{
  "data": {
    "a": {
      "slug": "gpt-oss-20b",
      "name": "gpt-oss-20b",
      "vendor": "OpenAI",
      "vendorUrl": "https://openai.com",
      "kind": "weights",
      "category": "open-weights",
      "summary": "gpt-oss-20b is OpenAI's open-weight mixture-of-experts reasoning model, 21B parameters with 3.6B active and a 131,072-token context, published on Hugging Face in MXFP4 under Apache 2.0 and trained on the harmony prompt format.",
      "url": "https://www.anchorterminal.com/tools/gpt-oss-20b",
      "markdownUrl": "https://www.anchorterminal.com/tools/gpt-oss-20b.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gpt-oss-20b.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gpt-oss-20b.json",
      "dns": "gpt-oss-20b.grade.anchorterminal.com",
      "repo": "https://huggingface.co/openai/gpt-oss-20b",
      "license": "Apache-2.0",
      "transports": [],
      "packages": [
        {
          "registry": "huggingface",
          "name": "openai/gpt-oss-20b"
        },
        {
          "registry": "ollama",
          "name": "gpt-oss:20b"
        },
        {
          "registry": "pypi",
          "name": "gpt-oss"
        },
        {
          "registry": "pypi",
          "name": "openai-harmony"
        }
      ],
      "auth": "none",
      "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-10-21).",
      "pricing": "free",
      "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0 with a one-line usage policy that asks users to comply with applicable law. Running it yourself costs the hardware, about 13.8 GB of weights, and OpenAI says it runs within 16 GB of memory (checked 2026-10-21).",
      "priceSummary": "Free",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-21).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-21"
      },
      "docsUrl": "https://huggingface.co/openai/gpt-oss-20b",
      "capabilities": [
        "model.open-weights"
      ],
      "tags": [
        "open-weights",
        "model",
        "moe",
        "reasoning",
        "tool-calling",
        "apache-2.0",
        "safetensors",
        "mxfp4",
        "self-hosted"
      ],
      "lastRelease": "2025-08-26",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 69.9,
        "grade": "B",
        "agentReady": false,
        "rank": 0,
        "ranked": false,
        "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools",
        "rankOf": 1524,
        "categoryRank": 6,
        "methodology": "0.8",
        "run": "2026-10-01",
        "scores": {
          "capability": 49,
          "interface": 90,
          "reach": 90,
          "risk": 85,
          "upkeep": 42
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "high",
          "date": "2026-11-01"
        },
        "negative": 0,
        "verdict": "gpt-oss-20b is a cousin for reasoning, coding and single tool calls with structured output, under plain Apache 2.0. It needs about 17 GB with a working context, and five inference providers serve it. The main risks are that it trails o4-mini at keeping system instructions above user ones, and OpenAI hasn't answered a report since August 2025.",
        "bestFor": "Local agents on a 24 GB GPU or Mac that want a permissive licence, wide runtime support and documented structured output, one tool call at a time",
        "strengths": [
          "Model code in released Transformers, vLLM, SGLang and llama.cpp, plus a 14 GB build in Ollama's library",
          "Fits a 24 GB machine at OpenAI's own MXFP4 precision, the one every evaluation used",
          "Apache 2.0 with no gate, no account and a usage policy that only asks users to follow the law",
          "Harmony guide documents tool declarations, call parsing, JSON Schema output and three reasoning levels, with OpenAI's own parser",
          "Trained on an instruction hierarchy against prompt injection, with OpenAI's results for it published"
        ],
        "weaknesses": [
          "No reply from OpenAI to any discussion since August 2025, and template reports wait unanswered",
          "One tool call per message",
          "Reasoning can be lowered but not switched off",
          "Only one quantised build from OpenAI, and its weights and template haven't changed since August 2025",
          "Safety results for this size are OpenAI's own, and it trails o4-mini on the instruction hierarchy"
        ],
        "agentNotes": [
          "Start it with `ollama run gpt-oss:20b` (the build that fits the reference machine), or `vllm serve openai/gpt-oss-20b` with a current vLLM release rather than the card's pinned vllm==0.10.1+gptoss wheel",
          "Use the harmony format through the chat template or openai-harmony; OpenAI says the model doesn't work correctly without it",
          "Parse tool calls and reasoning with openai-harmony; calls come on the commentary channel ending in `\u003c|call|\u003e`, reasoning on the analysis channel",
          "Set effort with `Reasoning: high` (or low, medium) in the system message, or `reasoning_effort` in the template; medium is the default",
          "Ask for JSON by putting a JSON Schema under `# Response Formats` in the developer message",
          "Drop earlier reasoning after a final answer but pass it back after tool calls, and don't show the analysis channel to users",
          "Expect one tool call per turn; run several in sequence rather than in parallel"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 3.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "high",
            "grade": "B",
            "methodology": "0.8",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 69.9
          }
        ],
        "editorialScores": {
          "capability": 49,
          "interface": 90,
          "reach": 90,
          "risk": 85,
          "upkeep": 42
        },
        "provenanceScore": 89,
        "checked": {
          "categories": {
            "capability": "2026-11-01",
            "interface": "2026-11-01",
            "reach": "2026-11-01",
            "risk": "2026-11-01",
            "upkeep": "2026-11-01"
          },
          "last": "2026-11-01",
          "oldest": "2026-11-01",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "ollama run gpt-oss:20b\n# or with vLLM:\nvllm serve openai/gpt-oss-20b\n# or, with llama.cpp and llama.cpp's own GGUF:\nllama-server -hf ggml-org/gpt-oss-20b-GGUF:MXFP4 --jinja",
        "http": "curl http://localhost:11434/api/chat \\\n  -d '{\"model\": \"gpt-oss:20b\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}]}'"
      },
      "letme": {
        "capability": "https://letme.dev/model.open-weights",
        "tool": "https://letme.dev/gpt-oss-20b"
      },
      "sameCompany": [
        "openai-api",
        "openai-embeddings",
        "openai-guardrails",
        "openai-moderation",
        "openai-image-api",
        "openai-sora",
        "openai-speech-to-text",
        "gpt-live",
        "openai-realtime",
        "openai-agents-sdk",
        "openai-decisions-api",
        "openai-agents-api",
        "openai-codex",
        "openai-dots",
        "gpt-oss-120b"
      ],
      "weights": {
        "trainedBy": "OpenAI",
        "params": "20.91B",
        "active": "3.61B",
        "context": 131072,
        "goodFor": "Text reasoning model for agents and coding, with function calling, built-in browser and Python tools and low, medium or high reasoning, in the harmony format.",
        "runtimes": [
          "llama.cpp",
          "Ollama",
          "vLLM",
          "SGLang",
          "Transformers"
        ],
        "builds": [
          {
            "name": "ggml-org gpt-oss-20b-GGUF (MXFP4)",
            "url": "https://huggingface.co/ggml-org/gpt-oss-20b-GGUF",
            "who": "llama.cpp",
            "precision": "mxfp4",
            "sizeGB": 12.11,
            "memoryGB": 16,
            "format": "gguf",
            "runsOn": [
              "llama.cpp"
            ],
            "note": "From ggml-org, the llama.cpp project's organisation. 12.11 GB of MXFP4 weights, from the Hub's model information on 10 November 2026. Recorded after the last grading, so Reach doesn't count it yet"
          },
          {
            "name": "gpt-oss-20b",
            "url": "https://huggingface.co/openai/gpt-oss-20b",
            "who": "publisher",
            "precision": "mxfp4",
            "sizeGB": 13.8,
            "memoryGB": 24,
            "format": "safetensors",
            "note": "MoE weights in MXFP4, the rest BF16, the precision OpenAI evaluated. original/ and metal/ hold the same weights for OpenAI's reference code. vLLM's gpt-oss recipe lists MI300x, MI325x, MI355x and Radeon AI PRO R9700 on AMD, not gfx1151"
          },
          {
            "name": "ollama gpt-oss:20b",
            "url": "https://ollama.com/library/gpt-oss:20b",
            "who": "ollama",
            "precision": "mxfp4",
            "sizeGB": 14,
            "memoryGB": 24,
            "format": "ollama",
            "runsOn": [
              "Ollama"
            ],
            "note": "OpenAI's MXFP4 weights; the card links it. Size as Ollama's tags page shows it, rounded to whole GB above 10 GB; the Linux build is the llama.cpp variant"
          }
        ],
        "run": "ollama run gpt-oss:20b",
        "runBuild": "ollama gpt-oss:20b",
        "checked": "2026-10-21",
        "minMemoryGB": 16
      },
      "family": {
        "lab": "OpenAI",
        "family": "gpt-oss",
        "url": "https://www.anchorterminal.com/open-weights/#openai",
        "others": [
          {
            "name": "gpt-oss-120b",
            "url": "https://huggingface.co/openai/gpt-oss-120b",
            "params": "117B total, 5.1B active (MoE)",
            "listing": "https://www.anchorterminal.com/tools/gpt-oss-120b"
          },
          {
            "name": "gpt-oss-safeguard-120b",
            "url": "https://huggingface.co/openai/gpt-oss-safeguard-120b",
            "params": "117B total, 5.1B active (MoE)"
          },
          {
            "name": "gpt-oss-safeguard-20b",
            "url": "https://huggingface.co/openai/gpt-oss-safeguard-20b",
            "params": "21B total, 3.6B active (MoE)"
          }
        ],
        "olderCount": 6,
        "unrestrictedCopies": 5
      },
      "area": "models",
      "provenance": {
        "legalEntity": "OpenAI (named in USAGE_POLICY and the model card; the LICENSE file's copyright line is the unfilled Apache template)",
        "domain": "openai.com",
        "domainRegistered": "2007-01-19",
        "domainNote": "openai.com was registered in 2007, years before the company was founded in 2015, so domain age flatters it.",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "https://huggingface.co/openai/gpt-oss-20b/commits/main",
        "securityTxt": "valid",
        "checked": "2026-10-21",
        "notes": [
          "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.",
          "The changelog is the repository's commit history, whose messages say what changed for some commits (the chat template on 7 and 8 August 2025, `\u003c|call|\u003e` as an end token on 13 August 2025) and not for others (README updates).",
          "openai.com/.well-known/security.txt answered 200, signed, with a Bugcrowd contact and a coordinated disclosure policy, but no Expires field, which RFC 9116 requires. Recorded as valid, as on the openai-api listing, since the data has no value for a file without one.",
          "openai.com/index/introducing-gpt-oss/ and openai.com/open-models/ answered 403 to our reader on 21 October 2026, so OpenAI's announcement wasn't read."
        ],
        "score": 89
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/gpt-oss-20b.json",
      "live": {
        "slug": "gpt-oss-20b",
        "versions": [
          {
            "registry": "pypi",
            "name": "gpt-oss",
            "version": "0.0.9",
            "released": "2026-01-13",
            "seenAt": "2026-11-15T11:18:35.03421037Z"
          },
          {
            "registry": "pypi",
            "name": "openai-harmony",
            "version": "0.0.8",
            "released": "2025-11-05",
            "seenAt": "2026-11-15T11:18:37.017294044Z"
          }
        ],
        "pypiWeekly": 8495,
        "securityTxt": {
          "url": "https://openai.com/.well-known/security.txt",
          "state": "valid",
          "checkedAt": "2026-11-14T16:17:34.617239149Z"
        },
        "domain": {
          "domain": "openai.com",
          "registered": "2007-01-19",
          "source": "https://rdap.verisign.com/com/v1/domain/openai.com",
          "checkedAt": "2026-11-08T14:52:04.4095079Z"
        },
        "pages": [
          {
            "url": "https://huggingface.co/openai/gpt-oss-20b/commits/main",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-11-14T19:07:06.137772685Z",
            "changedAt": "2026-11-14T19:07:06.137772685Z",
            "fingerprint": "218eb1390645"
          }
        ],
        "updatedAt": "2026-11-15T11:18:37.017294044Z"
      }
    },
    "answer": "gpt-oss-20b scores 69.9 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 3 of 4 scored categories. Inkling 2 Small leads on documentation and upkeep.",
    "b": {
      "slug": "inkling-2-small",
      "name": "Inkling 2 Small",
      "vendor": "Thinking Machines Lab",
      "vendorUrl": "https://thinkingmachines.ai",
      "kind": "weights",
      "category": "open-weights",
      "summary": "Inkling 2 Small is Thinking Machines Lab's open-weight mixture-of-experts model, 594B total and 17B active parameters, taking text and images and returning text, with adjustable thinking effort, published in NVFP4 and MXFP8 under Apache 2.0.",
      "url": "https://www.anchorterminal.com/tools/inkling-2-small",
      "markdownUrl": "https://www.anchorterminal.com/tools/inkling-2-small.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/inkling-2-small.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json",
      "dns": "inkling-2-small.grade.anchorterminal.com",
      "repo": "https://huggingface.co/thinkingmachines/Inkling-2-Small",
      "license": "Apache-2.0",
      "transports": [],
      "packages": [
        {
          "registry": "huggingface",
          "name": "thinkingmachines/Inkling-2-Small"
        },
        {
          "registry": "huggingface",
          "name": "thinkingmachines/Inkling-2-Small-MXFP8"
        }
      ],
      "auth": "none",
      "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither repository is gated (checked 2026-11-12). Thinking Machines' Model Acceptable Use Policy, linked from the card, says that downloading or using the weights binds you to it.",
      "pricing": "free",
      "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0 with Thinking Machines' Model Acceptable Use Policy on top. Running it yourself costs the hardware, 393.5 GB of files for the NVFP4 checkpoint and 622.8 GB for MXFP8, which Thinking Machines puts at 500 GB and 800 GB of GPU memory. Thinking Machines' Tinker serves it as a beta serverless inference API at $0.30 per million input tokens, $0.03 cached and $1.00 output (read 2026-11-06).",
      "priceSummary": "Free",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-12).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-12"
      },
      "docsUrl": "https://thinkingmachines.ai/model-card/inkling-2-small/",
      "capabilities": [
        "model.open-weights"
      ],
      "tags": [
        "open-weights",
        "model",
        "moe",
        "multimodal",
        "vision",
        "reasoning",
        "tool-calling",
        "apache-2.0",
        "safetensors",
        "nvfp4",
        "self-hosted",
        "new"
      ],
      "lastRelease": "2026-11-12",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 58.8,
        "grade": "C",
        "agentReady": false,
        "rank": 0,
        "ranked": false,
        "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools",
        "rankOf": 1524,
        "categoryRank": 78,
        "methodology": "0.8",
        "run": "2026-10-01",
        "scores": {
          "interface": 85,
          "reach": 40,
          "risk": 65,
          "upkeep": 67
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "low",
          "date": "2026-11-12"
        },
        "negative": 0,
        "verdict": "Thinking Machines' newest open model, a 594B mixture-of-experts generalist with images in, several tool calls a turn and per-request thinking effort. The NVFP4 checkpoint needs about 472 GB, and no released runtime runs it yet, so today that means vLLM's or SGLang's own images, or Tinker and Together hosted. The use policy binds on download and can change.",
        "bestFor": "Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image.",
        "strengths": [
          "Safetensors only, with a checksum on every LFS file in the publisher's own organisation",
          "Thinking effort set per request from none to xhigh, several tool calls a turn and a 1M-token context",
          "Two checkpoints from Thinking Machines, NVFP4 and MXFP8, under Apache 2.0 with no gate",
          "Thinking Machines' tml-renderers package renders prompts and parses tool calls for this model",
          "A training-content summary with sources, mix and an October 2026 collection cut-off",
          "Thinking Machines' own Tinker hosts it as beta serverless inference, and the card names seven more API providers"
        ],
        "weaknesses": [
          "The smaller checkpoint needs about 472 GB, and Thinking Machines says 500 GB of GPU memory",
          "No released version of vLLM, SGLang, Transformers, llama.cpp or Ollama runs it on 12 November 2026",
          "Apache 2.0 comes with an acceptable use policy that binds on download and can change at any time",
          "Safety results are Thinking Machines' own, with no harness to rerun them and no prompt-injection guidance",
          "Structured output isn't documented, and the card gives no dated knowledge cut-off",
          "No independent benchmark results were read, so Capability is pending and the total is capped at 61"
        ],
        "agentNotes": [
          "No released runtime runs it yet. Serve the NVFP4 checkpoint from SGLang's dev-inkling-2-small image with the cookbook's recipe for your hardware, or from vLLM's vllm/vllm-openai:inkling-2-small image",
          "In vLLM pass `--reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling`. In SGLang the tool-call parser is `inkling2` and the reasoning parser `inkling`",
          "Transformers' main branch loads only thinkingmachines/Inkling-2-Small-MXFP8, the 622.8 GB checkpoint, and no release has the code yet",
          "Pass `reasoning_effort` as none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99",
          "Effort none conditions the model toward no reasoning but doesn't forbid it, and higher effort needs a larger max_tokens",
          "Tool call arguments must reach the template as an object, not a JSON string, or it raises an error",
          "Images should be 40 to 4096 px a side. The model takes no audio, and the template raises an error for an audio part",
          "Use guided decoding or validate JSON yourself, since structured output isn't documented",
          "Without the hardware, call it on Tinker's OpenAI-compatible endpoint with a Tinker key, at $0.30 input and $1.00 output per million tokens as read on 6 November 2026",
          "Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "low",
            "grade": "C",
            "methodology": "0.8",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 58.8
          }
        ],
        "editorialScores": {
          "interface": 85,
          "reach": 40,
          "risk": 65,
          "upkeep": 67
        },
        "provenanceScore": 72,
        "checked": {
          "categories": {
            "interface": "2026-11-12",
            "reach": "2026-11-12",
            "risk": "2026-11-12",
            "upkeep": "2026-11-12"
          },
          "last": "2026-11-12",
          "lastMoved": "2026-11-12",
          "oldest": "2026-11-12",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "# per SGLang's cookbook, the NVFP4 checkpoint on 4 B300 GPUs. Not in an SGLang release yet,\n# so run it inside the lmsysorg/sglang:dev-inkling-2-small image:\nSGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=4096 sglang serve \\\n  --model-path thinkingmachines/Inkling-2-Small --tp 4 --ep 4 \\\n  --moe-a2a-backend megamoe --attention-backend fa4 --bf16-gemm-backend torch --dtype bfloat16 \\\n  --page-size 128 --grammar-backend xgrammar --enable-multimodal \\\n  --reasoning-parser inkling --tool-call-parser inkling2",
        "http": "curl http://localhost:30000/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"thinkingmachines/Inkling-2-Small\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n    \"reasoning_effort\": \"low\"\n  }'"
      },
      "letme": {
        "capability": "https://letme.dev/model.open-weights",
        "tool": "https://letme.dev/inkling-2-small"
      },
      "sameCompany": [
        "inkling",
        "inkling-small"
      ],
      "sameModel": [
        "tinker"
      ],
      "weights": {
        "trainedBy": "Thinking Machines Lab",
        "params": "594B",
        "active": "17B",
        "context": 1048576,
        "goodFor": "Mixture-of-experts generalist for coding, agents and tool use with images in, a 1M-token context and thinking effort set per request.",
        "runtimes": [],
        "builds": [
          {
            "name": "Inkling-2-Small",
            "url": "https://huggingface.co/thinkingmachines/Inkling-2-Small",
            "who": "publisher",
            "precision": "nvfp4",
            "sizeGB": 393.5,
            "memoryGB": 512,
            "format": "safetensors",
            "note": "The main checkpoint, in the precision the model was trained in. Routed experts in NVFP4 for layers 0 to 39 and MXFP8 for layers 40 to 47, per SGLang's cookbook. Thinking Machines states at least 500 GB of GPU memory"
          },
          {
            "name": "Inkling-2-Small-MXFP8",
            "url": "https://huggingface.co/thinkingmachines/Inkling-2-Small-MXFP8",
            "who": "publisher",
            "precision": "mxfp8",
            "sizeGB": 622.8,
            "memoryGB": 1024,
            "format": "safetensors",
            "note": "Every routed expert in MXFP8. Thinking Machines states at least 800 GB of GPU memory and recommends the NVFP4 checkpoint. It's the only checkpoint Transformers' main branch loads"
          }
        ],
        "run": "SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=4096 sglang serve --model-path thinkingmachines/Inkling-2-Small --tp 4 --ep 4 --moe-a2a-backend megamoe --attention-backend fa4 --bf16-gemm-backend torch --dtype bfloat16 --page-size 128 --grammar-backend xgrammar --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling2",
        "runBuild": "Inkling-2-Small",
        "checked": "2026-11-12",
        "minMemoryGB": 512
      },
      "family": {
        "lab": "Thinking Machines Lab",
        "family": "Inkling 2",
        "url": "https://www.anchorterminal.com/open-weights/#thinking-machines"
      },
      "area": "models",
      "provenance": {
        "legalEntity": "Thinking Machines Lab, Inc. (named as provider on its model card page and in its training-content summary)",
        "domain": "thinkingmachines.ai",
        "domainRegistered": "",
        "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "https://huggingface.co/thinkingmachines/Inkling-2-Small/commits/main",
        "securityTxt": "valid",
        "checked": "2026-11-12",
        "notes": [
          "Thinking Machines' model card page links both repositories in the thinkingmachines organisation on Hugging Face, which isn't verified by Hugging Face.",
          "Nothing is hosted for this listing, so the Apache 2.0 licence and the Model Acceptable Use Policy stand in for terms of service and no privacy policy is scored.",
          "The changelog is the repository's commit history, 3 commits on 12 November 2026, the upload, a library tag from a merged pull request and a card update.",
          "thinkingmachines.ai/.well-known/security.txt gives a security contact, a PGP key and an expiry in 2029, read on 12 November 2026, and the model card page links a coordinated vulnerability disclosure policy.",
          "Thinking Machines' terms bar scraping the Services. The founder decided on 6 November 2026 that reading at a person's pace is fine, so six pages were read one at a time on 12 November: the acceptable use policy, the training data page and its summary for this model, the model card page, and the tml-renderers and thinking effort guides. thinkingmachines.ai's robots.txt has no rules, and tinker-docs.thinkingmachines.ai answers 404 for robots.txt."
        ],
        "score": 72
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/inkling-2-small.json",
      "live": {
        "slug": "inkling-2-small",
        "probe": {
          "target": "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1",
          "method": "get",
          "lastAt": "2026-11-13T20:11:37.236512439Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 439,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 238,
          "p95ms24h": 467,
          "samples24h": 245,
          "samples30d": 1854,
          "days": [
            {
              "date": "2026-11-06",
              "probes": 186,
              "ok": 186
            },
            {
              "date": "2026-11-07",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-08",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-09",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-10",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-11",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-12",
              "probes": 245,
              "ok": 245
            },
            {
              "date": "2026-11-13",
              "probes": 206,
              "ok": 206
            }
          ],
          "since": "2026-11-06T00:00:00Z"
        },
        "securityTxt": {
          "url": "https://thinkingmachines.ai/.well-known/security.txt",
          "state": "valid",
          "expires": "2029-07-13T07:00:00.000Z",
          "checkedAt": "2026-11-14T16:19:22.779006645Z"
        },
        "llmsTxt": {
          "url": "https://tinker-docs.thinkingmachines.ai/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-13T15:54:36.79283015Z"
        },
        "domain": {
          "domain": "thinkingmachines.ai",
          "registered": "2024-07-09",
          "source": "https://rdap.identitydigital.services/rdap/domain/thinkingmachines.ai",
          "checkedAt": "2026-11-08T15:05:10.558189316Z"
        },
        "pages": [
          {
            "url": "https://huggingface.co/thinkingmachines/Inkling-2-Small/commits/main",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-11-14T19:07:35.812797752Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "39971da7a686"
          },
          {
            "url": "https://tinker-docs.thinkingmachines.ai/changelog/",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-11-13T18:32:58.088087394Z",
            "changedAt": "2026-11-13T18:32:58.088087394Z",
            "fingerprint": "c56006412e95"
          },
          {
            "url": "https://thinkingmachines.ai/legal/privacy/",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-13T18:32:53.884197991Z",
            "changedAt": "2026-11-06T13:43:40.660240815Z",
            "fingerprint": "3c33a4a74c61"
          },
          {
            "url": "https://thinkingmachines.ai/legal/terms/",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-13T18:32:56.034092745Z",
            "changedAt": "2026-11-06T13:43:42.918165055Z",
            "fingerprint": "08c6ceca5dbb"
          }
        ],
        "updatedAt": "2026-11-14T19:07:35.812797752Z"
      },
      "streak": {
        "days": 9,
        "from": "2026-11-06",
        "sinceWatching": true,
        "best": 9
      }
    },
    "edges": [
      {
        "by": 50,
        "category": "reach",
        "leads": "gpt-oss-20b",
        "name": "Reach",
        "reasons": {
          "a": "Memory earns 25, since OpenAI's own MXFP4 build is 13.76 GB and a fifth on top is 16.5 GB, just past the 16 GB band, and Ollama's 14 GB build lands in the same 24 GB band. Runtimes earn the full 25 from model code in released Transformers, vLLM and SGLang, the architecture in llama.cpp and the model in Ollama's library. Builds earn 10, because OpenAI ships one quantised precision, MXFP4, and the original and metal folders are the same weights for its reference code. Terms earn 15 for Apache 2.0, whose usage policy only asks users to follow the law. Download earns 10, since the repository isn't gated. Hosted earns 5, with five inference providers live for it on its Hugging Face page on 1 November 2026, while OpenAI's own API lists it with no usable rate limit and isn't counted.",
          "b": "Memory 0 of 30, the smallest build is Thinking Machines' NVFP4 checkpoint at 393.5 GB, about 472 GB with a fifth added, above the 256 GB line. Runtimes 0, no released version of the six runs it; vLLM and SGLang serve it from their own images and Transformers has it on its main branch only. Builds 15, two precisions from the publisher (NVFP4 and MXFP8). Terms 10, Apache 2.0 with a binding acceptable use policy on top, read as a custom licence. Download 10, no gate. Hosted 5, Thinking Machines' own Tinker serves it as beta serverless inference, and Together is live on Hugging Face. 0 + 0 + 15 + 10 + 10 + 5 = 40."
        },
        "scores": {
          "a": 90,
          "b": 40
        }
      },
      {
        "by": 25,
        "category": "upkeep",
        "leads": "inkling-2-small",
        "name": "Documentation and upkeep",
        "reasons": {
          "a": "The model card earns 17, covering six of the seven points and missing a statement of supported languages. Training data earns 10, a general description with a June 2024 cut-off and no sources or mix. Last change earns 5, because the files haven't changed since August 2025 and the reference code and harmony parser last changed on 1 and 5 November 2025, still within a year on 1 November 2026, while this year's commits only touch the browser tool, CI and a version number. Responsiveness earns 0, with no OpenAI reply to any of the 40 most recent discussions and none at all since August 2025. Version policy earns 5 for a first release kept in its own repository. File health earns 5, since template reports and an install report wait without a reply.",
          "b": "Model card 17 of 20, everything but a dated knowledge cut-off. Training data 15, an EU training-content summary with sources, mix, an October 2026 collection cut-off and filtering. Last change 20, the files were uploaded on 12 November 2026. Responsiveness 0, the repository has no questions yet, which reads as none answered. Version policy 5, a first release. File health 10, the files agree and no broken-file report waits. 17 + 15 + 20 + 0 + 5 + 10 = 67."
        },
        "scores": {
          "a": 42,
          "b": 67
        }
      },
      {
        "by": 20,
        "category": "risk",
        "leads": "gpt-oss-20b",
        "name": "Risk",
        "reasons": {
          "a": "File safety earns 25, since the weights are safetensors and metal/model.bin is OpenAI's own raw Metal format rather than pickle, and nothing in the repository runs as code (a judgement call on the .bin name). Provenance earns 15, files in OpenAI's own organisation and a checksum on every file. Safety evaluation earns 10, because the published safety results for this size are OpenAI's own, and the outside review covered gpt-oss-120b. Agent guidance earns 15 for an instruction hierarchy the model was trained to follow, with prompt-injection results, though OpenAI reports it trails o4-mini there. Licence risk keeps 15, with nothing to deduct under Apache 2.0. The security programme earns 5 for OpenAI's security.txt with a Bugcrowd contact. Public advisories for the gpt-oss code couldn't be checked, so that half scores as absent.",
          "b": "File safety 25, safetensors only and no repository code to run. Provenance 15, the files are in the organisation Thinking Machines links to, with a SHA-256 on every LFS file. Safety evaluation 10, Thinking Machines' own StrongREJECT, FORTRESS, HoneyBench and DistressBench results and described outside red-teaming, but nothing an outside party published or a harness to rerun. Agent guidance 5, the card names safeguards to add but doesn't say what its refusals cover, with nothing on prompt injection. Licence risk 5, 10 off for a use policy that reaches beyond the law and that can change at any time. Security programme 5, a security.txt and a disclosure policy, with public advisories unchecked and scored as absent. 25 + 15 + 10 + 5 + 5 + 5 = 65."
        },
        "scores": {
          "a": 85,
          "b": 65
        }
      },
      {
        "by": 5,
        "category": "interface",
        "leads": "gpt-oss-20b",
        "name": "Agent interface",
        "reasons": {
          "a": "The chat template earns 20, a Jinja file in the repository. The tool-calling format earns 25, since OpenAI's harmony guide says how functions are declared and how calls come back, and OpenAI ships the openai-harmony parser. Trained tool calling earns 10, because each call ends the message and waits for its result, so it makes one call at a time. Structured output earns 15 for a JSON Schema given in the developer message, documented in the harmony guide. Reasoning control earns 10, with low, medium or high effort per request and the reasoning on its own channel, though it can't be switched off. Context earns 10 for 131,072 tokens, which OpenAI describes as trained in even though the config reaches it with YaRN.",
          "b": "Chat template 20, a Jinja file in the repository. Tool-calling format 25, Thinking Machines' tml-renderers guide shows how tools are declared and how calls come back for this model, and its package ships the parser. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, thinking effort is set per request from none to xhigh, and the reasoning comes back in reasoning_content. Context 10, up to 1M tokens. 20 + 25 + 20 + 0 + 10 + 10 = 85."
        },
        "scores": {
          "a": 90,
          "b": 85
        }
      }
    ],
    "facts": [
      {
        "a": "Open-weight model",
        "b": "Open-weight model",
        "name": "Kind"
      },
      {
        "a": "OpenAI",
        "b": "Thinking Machines Lab",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "",
        "b": "",
        "name": "Transports"
      },
      {
        "a": "None",
        "b": "None",
        "name": "Auth"
      },
      {
        "a": "Free",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Apache-2.0",
        "b": "Apache-2.0",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "no",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "2025-08-26",
        "b": "2026-11-12",
        "name": "Last release"
      },
      {
        "a": "no document linked",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "no document linked",
        "b": "no document linked",
        "name": "Privacy policy last updated"
      },
      {
        "a": "3.5/5 (4)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "gpt-oss-20b scores 69.9 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 3 of 4 scored categories. Inkling 2 Small leads on documentation and upkeep.",
        "question": "Which is better for AI agents, gpt-oss-20b or Inkling 2 Small?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reach, 90 against 40",
          "Risk, 85 against 65",
          "Agent interface, 90 against 85"
        ],
        "also": null,
        "goodFor": "Local agents on a 24 GB GPU or Mac that want a permissive licence, wide runtime support and documented structured output, one tool call at a time",
        "slug": "gpt-oss-20b",
        "watchFor": "No reply from OpenAI to any discussion since August 2025, and template reports wait unanswered"
      },
      {
        "aheadOn": [
          "Documentation and upkeep, 67 against 42"
        ],
        "also": null,
        "goodFor": "Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image.",
        "slug": "inkling-2-small",
        "watchFor": "The smaller checkpoint needs about 472 GB, and Thinking Machines says 500 GB of GPU memory"
      }
    ],
    "history": {
      "gpt-oss-20b": null,
      "inkling-2-small": [
        {
          "causes": [
            "product"
          ],
          "date": "2026-11-12",
          "delta": 6.7,
          "from": 52.1,
          "fromGrade": "D",
          "to": 58.8,
          "toGrade": "C"
        }
      ]
    },
    "job": {
      "capability": "model.open-weights",
      "name": "Open-weight models you run yourself"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-gpt-oss-20b.json",
        "title": "Agents-A1-4B vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling-2-small.json",
        "title": "Agents-A1-4B vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-gpt-oss-20b.json",
        "title": "Apertus v1.5 8B vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling-2-small.json",
        "title": "Apertus v1.5 8B vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-gpt-oss-20b.json",
        "title": "Apodex-1.1-mini vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling-2-small.json",
        "title": "Apodex-1.1-mini vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/arete-27b-vs-gpt-oss-20b.json",
        "title": "Arete-27B vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/arete-27b-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/arete-27b-vs-inkling-2-small.json",
        "title": "Arete-27B vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/arete-27b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-gpt-oss-20b.json",
        "title": "BigBang-v1 vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling-2-small.json",
        "title": "BigBang-v1 vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/carbon-x-vs-gpt-oss-20b.json",
        "title": "Carbon-X vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/carbon-x-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling-2-small.json",
        "title": "Carbon-X vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cola2-vs-gpt-oss-20b.json",
        "title": "Cola2 vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/cola2-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cola2-vs-inkling-2-small.json",
        "title": "Cola2 vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/cola2-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-gpt-oss-20b.json",
        "title": "Cosmos-Reason2-2B vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling-2-small.json",
        "title": "Cosmos-Reason2-2B vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-gpt-oss-20b.json",
        "title": "Darwin-36B-Opus vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling-2-small.json",
        "title": "Darwin-36B-Opus vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gpt-oss-20b.json",
        "title": "DeepSeek-V3.2 vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-2-small.json",
        "title": "DeepSeek-V3.2 vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-gpt-oss-20b.json",
        "title": "DeepSeek V4.1 Flash vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling-2-small.json",
        "title": "DeepSeek V4.1 Flash vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-gpt-oss-20b.json",
        "title": "DeepSeek-V4-Flash-0731 vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling-2-small.json",
        "title": "DeepSeek-V4-Flash-0731 vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-20b.json",
        "title": "Devstral Small 2 vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-2-small.json",
        "title": "Devstral Small 2 vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gpt-oss-20b.json",
        "title": "DiffusionGemma 26B A4B IT vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-2-small.json",
        "title": "DiffusionGemma 26B A4B IT vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-gpt-oss-20b.json",
        "title": "EXAONE 4.5 33B vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-inkling-2-small.json",
        "title": "EXAONE 4.5 33B vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gpt-oss-20b.json",
        "title": "Gemma 4 12B IT vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling-2-small.json",
        "title": "Gemma 4 12B IT vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-gpt-oss-20b.json",
        "title": "Gemma 4 26B A4B IT vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling-2-small.json",
        "title": "Gemma 4 26B A4B IT vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-gpt-oss-20b.json",
        "title": "Gemma 4 31B IT vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling-2-small.json",
        "title": "Gemma 4 31B IT vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-gpt-oss-20b.json",
        "title": "Gemma 4 E2B IT vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling-2-small.json",
        "title": "Gemma 4 E2B IT vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-gpt-oss-20b.json",
        "title": "Gemma 4 E4B IT vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling-2-small.json",
        "title": "Gemma 4 E4B IT vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-gpt-oss-20b.json",
        "title": "GLM-4.5-Air vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling-2-small.json",
        "title": "GLM-4.5-Air vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-gpt-oss-20b.json",
        "title": "GLM-4.7-Flash vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling-2-small.json",
        "title": "GLM-4.7-Flash vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-gpt-oss-20b.json",
        "title": "GLM-5.3-Flash vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-2-small.json",
        "title": "GLM-5.3-Flash vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-gpt-oss-20b.json",
        "title": "GLM-5.3 vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-2-small.json",
        "title": "GLM-5.3 vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-gpt-oss-20b.json",
        "title": "gpt-oss-120b vs gpt-oss-20b",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-gpt-oss-20b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling-2-small.json",
        "title": "gpt-oss-120b vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-granite-4-2-30b.json",
        "title": "gpt-oss-20b vs Granite 4.2 30B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-granite-4-2-30b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-granite-4-2-3b.json",
        "title": "gpt-oss-20b vs Granite 4.2 3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-granite-4-2-3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-granite-4-2-8b.json",
        "title": "gpt-oss-20b vs Granite 4.2 8B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-granite-4-2-8b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy-memory-30b-a3b.json",
        "title": "gpt-oss-20b vs Hy-Memory-30B-A3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy-memory-30b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy3.json",
        "title": "gpt-oss-20b vs Hy3",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy3"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling.json",
        "title": "gpt-oss-20b vs Inkling",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-small.json",
        "title": "gpt-oss-20b vs Inkling-Small",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-internvl3-5-gpt-oss-20b-a4b-preview.json",
        "title": "gpt-oss-20b vs InternVL3.5-GPT-OSS-20B-A4B-Preview",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-internvl3-5-gpt-oss-20b-a4b-preview"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kimi-k3.json",
        "title": "gpt-oss-20b vs Kimi K3",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kimi-k3"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kimi-k3-1-pro.json",
        "title": "gpt-oss-20b vs Kimi K3.1 Pro",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kimi-k3-1-pro"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kolibri-1.json",
        "title": "gpt-oss-20b vs Kolibri-1",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kolibri-1"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kronos.json",
        "title": "gpt-oss-20b vs Kronos",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kronos"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-laguna-m-1.json",
        "title": "gpt-oss-20b vs Laguna M.1",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-laguna-m-1"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-laguna-s-2-1.json",
        "title": "gpt-oss-20b vs Laguna S 2.1",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-laguna-s-2-1"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-laguna-xs-2-1.json",
        "title": "gpt-oss-20b vs Laguna XS 2.1",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-laguna-xs-2-1"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lbs-27b.json",
        "title": "gpt-oss-20b vs LBS-27B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lbs-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm2-5-2-6b.json",
        "title": "gpt-oss-20b vs LFM2.5-2.6B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm2-5-2-6b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-1-7b.json",
        "title": "gpt-oss-20b vs LFM3-1.7B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-1-7b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-audio-2b.json",
        "title": "gpt-oss-20b vs LFM3-Audio-2B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-audio-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-omni-2b.json",
        "title": "gpt-oss-20b vs LFM3-Omni-2B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-omni-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-vl-2b.json",
        "title": "gpt-oss-20b vs LFM3-VL-2B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-vl-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ling-3-0-tiny.json",
        "title": "gpt-oss-20b vs Ling-3.0-tiny",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ling-3-0-tiny"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ling-3-1-flash-1019.json",
        "title": "gpt-oss-20b vs Ling-3.1-flash-1019",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ling-3-1-flash-1019"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-longcat-2-5.json",
        "title": "gpt-oss-20b vs LongCat-2.5",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-longcat-2-5"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-mimo-v2-6-distill-qwen-9b.json",
        "title": "gpt-oss-20b vs MiMo-V2.6 Distill Qwen 9B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-mimo-v2-6-distill-qwen-9b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-mimo-v2-6-flash-rl.json",
        "title": "gpt-oss-20b vs MiMo-V2.6-Flash-RL",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-mimo-v2-6-flash-rl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-o-4-5.json",
        "title": "gpt-oss-20b vs MiniCPM-o 4.5",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-o-4-5"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-v-4-7-1b.json",
        "title": "gpt-oss-20b vs MiniCPM-V 4.7 1B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-v-4-7-1b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-v-4-7-35b-a3b.json",
        "title": "gpt-oss-20b vs MiniCPM-V 4.7 35B-A3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-v-4-7-35b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm5-2b.json",
        "title": "gpt-oss-20b vs MiniCPM5-2B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm5-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minimax-m2-5.json",
        "title": "gpt-oss-20b vs MiniMax-M2.5",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minimax-m2-5"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minimax-m2-7.json",
        "title": "gpt-oss-20b vs MiniMax-M2.7",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minimax-m2-7"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minimax-m3-1-flash.json",
        "title": "gpt-oss-20b vs MiniMax-M3.1-Flash",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minimax-m3-1-flash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-mistral-large-4.json",
        "title": "gpt-oss-20b vs Mistral Large 4",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-mistral-large-4"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-muse-glimmer-30b.json",
        "title": "gpt-oss-20b vs Muse Glimmer 30B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-muse-glimmer-30b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nanbeige-4-2-3b.json",
        "title": "gpt-oss-20b vs Nanbeige4.2-3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nanbeige-4-2-3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nanbeige-4-3-33b.json",
        "title": "gpt-oss-20b vs Nanbeige4.3-33B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nanbeige-4-3-33b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-5-bolt-e4b-4gb.json",
        "title": "gpt-oss-20b vs NVIDIA Nemotron 3.5 Bolt E4B 4GB",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-5-bolt-e4b-4gb"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-5-lightning-30b-a3b.json",
        "title": "gpt-oss-20b vs Nemotron 3.5 Lightning 30B A3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-5-lightning-30b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-nano-30b-a3b.json",
        "title": "gpt-oss-20b vs Nemotron 3 Nano 30B A3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-nano-30b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-nano-4b.json",
        "title": "gpt-oss-20b vs Nemotron 3 Nano 4B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-nano-4b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json",
        "title": "gpt-oss-20b vs Nemotron 3 Nano Omni 30B A3B Reasoning",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-nano-omni-30b-a3b-reasoning"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-super-120b-a12b.json",
        "title": "gpt-oss-20b vs Nemotron 3 Super 120B A12B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-super-120b-a12b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-ultra-550b-a55b.json",
        "title": "gpt-oss-20b vs Nemotron 3 Ultra 550B A55B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-ultra-550b-a55b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-north-mini-code-1-0.json",
        "title": "gpt-oss-20b vs North Mini Code 1.0",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-north-mini-code-1-0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-occamy-1-0.json",
        "title": "gpt-oss-20b vs occamy-1.0",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-occamy-1-0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-olmo-3-7b-think.json",
        "title": "gpt-oss-20b vs Olmo 3 7B Think",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-olmo-3-7b-think"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-122b.json",
        "title": "gpt-oss-20b vs Ornith-1.5-122B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-122b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-35b-a3b.json",
        "title": "gpt-oss-20b vs Ornith-1.5-35B-A3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-35b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-397b.json",
        "title": "gpt-oss-20b vs Ornith-1.5-397B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-397b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-9b.json",
        "title": "gpt-oss-20b vs Ornith-1.5-9B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-9b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-otel-2-0-llm-31b-it.json",
        "title": "gpt-oss-20b vs OTel-2.0-LLM-31B-IT",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-otel-2-0-llm-31b-it"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen-agentworld-35b-a3b.json",
        "title": "gpt-oss-20b vs Qwen-AgentWorld-35B-A3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen-agentworld-35b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-30b-a3b-instruct-2507.json",
        "title": "gpt-oss-20b vs Qwen3-30B-A3B-Instruct-2507",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-30b-a3b-instruct-2507"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-4b-instruct-2507.json",
        "title": "gpt-oss-20b vs Qwen3-4B-Instruct-2507",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-4b-instruct-2507"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-0-8b.json",
        "title": "gpt-oss-20b vs Qwen3.5-0.8B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-0-8b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-122b-a10b.json",
        "title": "gpt-oss-20b vs Qwen3.5-122B-A10B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-122b-a10b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-2b.json",
        "title": "gpt-oss-20b vs Qwen3.5-2B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-397b-a17b.json",
        "title": "gpt-oss-20b vs Qwen3.5-397B-A17B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-397b-a17b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-4b.json",
        "title": "gpt-oss-20b vs Qwen3.5-4B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-4b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-9b.json",
        "title": "gpt-oss-20b vs Qwen3.5-9B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-9b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-6-27b.json",
        "title": "gpt-oss-20b vs Qwen3.6-27B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-6-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-6-35b-a3b.json",
        "title": "gpt-oss-20b vs Qwen3.6-35B-A3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-6-35b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-8-27b.json",
        "title": "gpt-oss-20b vs Qwen3.8-27B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-8-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-8-flash-next.json",
        "title": "gpt-oss-20b vs Qwen3.8-Flash-Next",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-8-flash-next"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-coder-30b-a3b-instruct.json",
        "title": "gpt-oss-20b vs Qwen3-Coder-30B-A3B-Instruct",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-coder-30b-a3b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-coder-next.json",
        "title": "gpt-oss-20b vs Qwen3-Coder-Next",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-coder-next"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-omni-30b-a3b-instruct.json",
        "title": "gpt-oss-20b vs Qwen3-Omni-30B-A3B-Instruct",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-omni-30b-a3b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-2b-instruct.json",
        "title": "gpt-oss-20b vs Qwen3-VL-2B-Instruct",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-2b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-30b-a3b-instruct.json",
        "title": "gpt-oss-20b vs Qwen3-VL-30B-A3B-Instruct",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-30b-a3b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-32b-instruct.json",
        "title": "gpt-oss-20b vs Qwen3-VL-32B-Instruct",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-32b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-4b-instruct.json",
        "title": "gpt-oss-20b vs Qwen3-VL-4B-Instruct",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-4b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-8b-instruct.json",
        "title": "gpt-oss-20b vs Qwen3-VL-8B-Instruct",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-8b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwopus3-8-27b-flash-v2.json",
        "title": "gpt-oss-20b vs Qwopus3.8-27B-Flash-V2",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwopus3-8-27b-flash-v2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-recursive-flint.json",
        "title": "gpt-oss-20b vs Recursive Flint",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-recursive-flint"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ripple-65b-preview.json",
        "title": "gpt-oss-20b vs Ripple-65B Preview",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ripple-65b-preview"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-sensenova-loop-9b-preview.json",
        "title": "gpt-oss-20b vs SenseNova-Loop-9B-Preview",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-sensenova-loop-9b-preview"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-smollm3-3b.json",
        "title": "gpt-oss-20b vs SmolLM3-3B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-smollm3-3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-spark-x2-6-4b.json",
        "title": "gpt-oss-20b vs Spark-X2.6-4B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-spark-x2-6-4b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-step-3-7-flash.json",
        "title": "gpt-oss-20b vs Step 3.7 Flash",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-step-3-7-flash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-swift-1-5-qwen3-8-27b.json",
        "title": "gpt-oss-20b vs Swift 1.5 Qwen3.8-27B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-swift-1-5-qwen3-8-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-swift-1-5-qwen3-8-flash-next.json",
        "title": "gpt-oss-20b vs Swift 1.5 Qwen3.8-Flash-Next",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-swift-1-5-qwen3-8-flash-next"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-thinkingcap-qwen3-8-27b.json",
        "title": "gpt-oss-20b vs ThinkingCap (Qwen3.8 27B)",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-thinkingcap-qwen3-8-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-unlimited-ocr-2.json",
        "title": "gpt-oss-20b vs Baidu Unlimited-OCR-2",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-unlimited-ocr-2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-wevisone-vl-2b.json",
        "title": "gpt-oss-20b vs WeVisOne-VL-2B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-wevisone-vl-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-wevisone-vl-4b.json",
        "title": "gpt-oss-20b vs WeVisOne-VL-4B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-wevisone-vl-4b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-zaya1-8b.json",
        "title": "gpt-oss-20b vs ZAYA1-8B",
        "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-zaya1-8b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-inkling-2-small.json",
        "title": "Granite 4.2 30B vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-2-small.json",
        "title": "Granite 4.2 3B vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-inkling-2-small.json",
        "title": "Granite 4.2 8B vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-inkling-2-small.json",
        "title": "Hy-Memory-30B-A3B vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hy3-vs-inkling-2-small.json",
        "title": "Hy3 vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/hy3-vs-inkling-2-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-inkling-small.json",
        "title": "Inkling 2 Small vs Inkling-Small",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-inkling-small"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-internvl3-5-gpt-oss-20b-a4b-preview.json",
        "title": "Inkling 2 Small vs InternVL3.5-GPT-OSS-20B-A4B-Preview",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-internvl3-5-gpt-oss-20b-a4b-preview"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3.json",
        "title": "Inkling 2 Small vs Kimi K3",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3-1-pro.json",
        "title": "Inkling 2 Small vs Kimi K3.1 Pro",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3-1-pro"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kolibri-1.json",
        "title": "Inkling 2 Small vs Kolibri-1",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kolibri-1"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kronos.json",
        "title": "Inkling 2 Small vs Kronos",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-kronos"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-m-1.json",
        "title": "Inkling 2 Small vs Laguna M.1",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-m-1"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-s-2-1.json",
        "title": "Inkling 2 Small vs Laguna S 2.1",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-s-2-1"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-xs-2-1.json",
        "title": "Inkling 2 Small vs Laguna XS 2.1",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-xs-2-1"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lbs-27b.json",
        "title": "Inkling 2 Small vs LBS-27B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lbs-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm2-5-2-6b.json",
        "title": "Inkling 2 Small vs LFM2.5-2.6B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm2-5-2-6b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-1-7b.json",
        "title": "Inkling 2 Small vs LFM3-1.7B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-1-7b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-audio-2b.json",
        "title": "Inkling 2 Small vs LFM3-Audio-2B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-audio-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-omni-2b.json",
        "title": "Inkling 2 Small vs LFM3-Omni-2B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-omni-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-vl-2b.json",
        "title": "Inkling 2 Small vs LFM3-VL-2B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-vl-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-0-tiny.json",
        "title": "Inkling 2 Small vs Ling-3.0-tiny",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-0-tiny"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-1-flash-1019.json",
        "title": "Inkling 2 Small vs Ling-3.1-flash-1019",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-1-flash-1019"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-longcat-2-5.json",
        "title": "Inkling 2 Small vs LongCat-2.5",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-longcat-2-5"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-distill-qwen-9b.json",
        "title": "Inkling 2 Small vs MiMo-V2.6 Distill Qwen 9B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-distill-qwen-9b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-flash-rl.json",
        "title": "Inkling 2 Small vs MiMo-V2.6-Flash-RL",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-flash-rl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-o-4-5.json",
        "title": "Inkling 2 Small vs MiniCPM-o 4.5",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-o-4-5"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-1b.json",
        "title": "Inkling 2 Small vs MiniCPM-V 4.7 1B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-1b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-35b-a3b.json",
        "title": "Inkling 2 Small vs MiniCPM-V 4.7 35B-A3B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-35b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm5-2b.json",
        "title": "Inkling 2 Small vs MiniCPM5-2B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm5-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-5.json",
        "title": "Inkling 2 Small vs MiniMax-M2.5",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-5"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-7.json",
        "title": "Inkling 2 Small vs MiniMax-M2.7",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-7"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m3-1-flash.json",
        "title": "Inkling 2 Small vs MiniMax-M3.1-Flash",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m3-1-flash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-large-4.json",
        "title": "Inkling 2 Small vs Mistral Large 4",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-large-4"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-glimmer-30b.json",
        "title": "Inkling 2 Small vs Muse Glimmer 30B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-glimmer-30b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-2-3b.json",
        "title": "Inkling 2 Small vs Nanbeige4.2-3B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-2-3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-3-33b.json",
        "title": "Inkling 2 Small vs Nanbeige4.3-33B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-3-33b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-bolt-e4b-4gb.json",
        "title": "Inkling 2 Small vs NVIDIA Nemotron 3.5 Bolt E4B 4GB",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-bolt-e4b-4gb"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-lightning-30b-a3b.json",
        "title": "Inkling 2 Small vs Nemotron 3.5 Lightning 30B A3B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-lightning-30b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-30b-a3b.json",
        "title": "Inkling 2 Small vs Nemotron 3 Nano 30B A3B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-30b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-4b.json",
        "title": "Inkling 2 Small vs Nemotron 3 Nano 4B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-4b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json",
        "title": "Inkling 2 Small vs Nemotron 3 Nano Omni 30B A3B Reasoning",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-omni-30b-a3b-reasoning"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-super-120b-a12b.json",
        "title": "Inkling 2 Small vs Nemotron 3 Super 120B A12B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-super-120b-a12b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-ultra-550b-a55b.json",
        "title": "Inkling 2 Small vs Nemotron 3 Ultra 550B A55B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-ultra-550b-a55b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-north-mini-code-1-0.json",
        "title": "Inkling 2 Small vs North Mini Code 1.0",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-north-mini-code-1-0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-occamy-1-0.json",
        "title": "Inkling 2 Small vs occamy-1.0",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-occamy-1-0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-olmo-3-7b-think.json",
        "title": "Inkling 2 Small vs Olmo 3 7B Think",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-olmo-3-7b-think"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-122b.json",
        "title": "Inkling 2 Small vs Ornith-1.5-122B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-122b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-35b-a3b.json",
        "title": "Inkling 2 Small vs Ornith-1.5-35B-A3B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-35b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-397b.json",
        "title": "Inkling 2 Small vs Ornith-1.5-397B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-397b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-9b.json",
        "title": "Inkling 2 Small vs Ornith-1.5-9B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-9b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-otel-2-0-llm-31b-it.json",
        "title": "Inkling 2 Small vs OTel-2.0-LLM-31B-IT",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-otel-2-0-llm-31b-it"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen-agentworld-35b-a3b.json",
        "title": "Inkling 2 Small vs Qwen-AgentWorld-35B-A3B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen-agentworld-35b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-30b-a3b-instruct-2507.json",
        "title": "Inkling 2 Small vs Qwen3-30B-A3B-Instruct-2507",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-30b-a3b-instruct-2507"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-4b-instruct-2507.json",
        "title": "Inkling 2 Small vs Qwen3-4B-Instruct-2507",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-4b-instruct-2507"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-0-8b.json",
        "title": "Inkling 2 Small vs Qwen3.5-0.8B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-0-8b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-122b-a10b.json",
        "title": "Inkling 2 Small vs Qwen3.5-122B-A10B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-122b-a10b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-2b.json",
        "title": "Inkling 2 Small vs Qwen3.5-2B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-397b-a17b.json",
        "title": "Inkling 2 Small vs Qwen3.5-397B-A17B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-397b-a17b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-4b.json",
        "title": "Inkling 2 Small vs Qwen3.5-4B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-4b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-9b.json",
        "title": "Inkling 2 Small vs Qwen3.5-9B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-9b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-27b.json",
        "title": "Inkling 2 Small vs Qwen3.6-27B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-35b-a3b.json",
        "title": "Inkling 2 Small vs Qwen3.6-35B-A3B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-35b-a3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-27b.json",
        "title": "Inkling 2 Small vs Qwen3.8-27B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-flash-next.json",
        "title": "Inkling 2 Small vs Qwen3.8-Flash-Next",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-flash-next"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-30b-a3b-instruct.json",
        "title": "Inkling 2 Small vs Qwen3-Coder-30B-A3B-Instruct",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-30b-a3b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-next.json",
        "title": "Inkling 2 Small vs Qwen3-Coder-Next",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-next"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-omni-30b-a3b-instruct.json",
        "title": "Inkling 2 Small vs Qwen3-Omni-30B-A3B-Instruct",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-omni-30b-a3b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-2b-instruct.json",
        "title": "Inkling 2 Small vs Qwen3-VL-2B-Instruct",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-2b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-30b-a3b-instruct.json",
        "title": "Inkling 2 Small vs Qwen3-VL-30B-A3B-Instruct",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-30b-a3b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-32b-instruct.json",
        "title": "Inkling 2 Small vs Qwen3-VL-32B-Instruct",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-32b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-4b-instruct.json",
        "title": "Inkling 2 Small vs Qwen3-VL-4B-Instruct",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-4b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-8b-instruct.json",
        "title": "Inkling 2 Small vs Qwen3-VL-8B-Instruct",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-8b-instruct"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwopus3-8-27b-flash-v2.json",
        "title": "Inkling 2 Small vs Qwopus3.8-27B-Flash-V2",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-qwopus3-8-27b-flash-v2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-recursive-flint.json",
        "title": "Inkling 2 Small vs Recursive Flint",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-recursive-flint"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ripple-65b-preview.json",
        "title": "Inkling 2 Small vs Ripple-65B Preview",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ripple-65b-preview"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-sensenova-loop-9b-preview.json",
        "title": "Inkling 2 Small vs SenseNova-Loop-9B-Preview",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-sensenova-loop-9b-preview"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-smollm3-3b.json",
        "title": "Inkling 2 Small vs SmolLM3-3B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-smollm3-3b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-spark-x2-6-4b.json",
        "title": "Inkling 2 Small vs Spark-X2.6-4B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-spark-x2-6-4b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-step-3-7-flash.json",
        "title": "Inkling 2 Small vs Step 3.7 Flash",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-step-3-7-flash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-27b.json",
        "title": "Inkling 2 Small vs Swift 1.5 Qwen3.8-27B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-flash-next.json",
        "title": "Inkling 2 Small vs Swift 1.5 Qwen3.8-Flash-Next",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-flash-next"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-thinkingcap-qwen3-8-27b.json",
        "title": "Inkling 2 Small vs ThinkingCap (Qwen3.8 27B)",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-thinkingcap-qwen3-8-27b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-unlimited-ocr-2.json",
        "title": "Inkling 2 Small vs Baidu Unlimited-OCR-2",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-unlimited-ocr-2"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-2b.json",
        "title": "Inkling 2 Small vs WeVisOne-VL-2B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-4b.json",
        "title": "Inkling 2 Small vs WeVisOne-VL-4B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-4b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-zaya1-8b.json",
        "title": "Inkling 2 Small vs ZAYA1-8B",
        "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-zaya1-8b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/inkling-vs-inkling-2-small.json",
        "title": "Inkling vs Inkling 2 Small",
        "url": "https://www.anchorterminal.com/compare/inkling-vs-inkling-2-small"
      }
    ],
    "panel": null,
    "scores": [
      {
        "key": "capability",
        "name": "Capability",
        "pending": true,
        "weight": 35
      },
      {
        "by": 50,
        "edge": "gpt-oss-20b",
        "gpt-oss-20b": 90,
        "inkling-2-small": 40,
        "key": "reach",
        "name": "Reach",
        "weight": 25
      },
      {
        "by": 20,
        "edge": "gpt-oss-20b",
        "gpt-oss-20b": 85,
        "inkling-2-small": 65,
        "key": "risk",
        "name": "Risk",
        "weight": 20
      },
      {
        "by": 5,
        "edge": "gpt-oss-20b",
        "gpt-oss-20b": 90,
        "inkling-2-small": 85,
        "key": "interface",
        "name": "Agent interface",
        "weight": 10
      },
      {
        "by": 25,
        "edge": "inkling-2-small",
        "gpt-oss-20b": 42,
        "inkling-2-small": 67,
        "key": "upkeep",
        "name": "Documentation and upkeep",
        "weight": 10
      }
    ],
    "summary": "gpt-oss-20b scores 69.9 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 3 of 4 scored categories. Inkling 2 Small leads on documentation and upkeep. Both do open-weight models you run yourself.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "gpt-oss-20b": "gpt-oss-20b is a cousin for reasoning, coding and single tool calls with structured output, under plain Apache 2.0. It needs about 17 GB with a working context, and five inference providers serve it. The main risks are that it trails o4-mini at keeping system instructions above user ones, and OpenAI hasn't answered a report since August 2025.",
      "inkling-2-small": "Thinking Machines' newest open model, a 594B mixture-of-experts generalist with images in, several tool calls a turn and per-request thinking effort. The NVFP4 checkpoint needs about 472 GB, and no released runtime runs it yet, so today that means vLLM's or SGLang's own images, or Tinker and Together hosted. The use policy binds on download and can change."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small",
    "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small.min.md"
  },
  "markdown": "gpt-oss-20b scores 69.9 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 3 of 4 scored categories. Inkling 2 Small leads on documentation and upkeep. Both do open-weight models you run yourself.\n\n- gpt-oss-20b: grade B, 69.9/100, rank #8 of 161 open-weight models. Markdown https://www.anchorterminal.com/tools/gpt-oss-20b.md · JSON https://www.anchorterminal.com/api/v1/tools/gpt-oss-20b.json\n- Inkling 2 Small: grade C, 58.8/100, rank #102 of 161 open-weight models. Markdown https://www.anchorterminal.com/tools/inkling-2-small.md · JSON https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json\n- Best open-weight models you download and run yourself for AI agents: https://www.anchorterminal.com/best/open-weights/index.md\n- All 6472 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### gpt-oss-20b (B)\n\nGood for: Local agents on a 24 GB GPU or Mac that want a permissive licence, wide runtime support and documented structured output, one tool call at a time\n\nAhead on:\n- Reach, 90 against 40\n- Risk, 85 against 65\n- Agent interface, 90 against 85\n\nWatch for: No reply from OpenAI to any discussion since August 2025, and template reports wait unanswered\n\n### Inkling 2 Small (C)\n\nGood for: Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image.\n\nAhead on:\n- Documentation and upkeep, 67 against 42\n\nWatch for: The smaller checkpoint needs about 472 GB, and Thinking Machines says 500 GB of GPU memory\n\n\n## Why the edge\n\n### Reach: gpt-oss-20b +50\n\n- gpt-oss-20b (90): Memory earns 25, since OpenAI's own MXFP4 build is 13.76 GB and a fifth on top is 16.5 GB, just past the 16 GB band, and Ollama's 14 GB build lands in the same 24 GB band. Runtimes earn the full 25 from model code in released Transformers, vLLM and SGLang, the architecture in llama.cpp and the model in Ollama's library. Builds earn 10, because OpenAI ships one quantised precision, MXFP4, and the original and metal folders are the same weights for its reference code. Terms earn 15 for Apache 2.0, whose usage policy only asks users to follow the law. Download earns 10, since the repository isn't gated. Hosted earns 5, with five inference providers live for it on its Hugging Face page on 1 November 2026, while OpenAI's own API lists it with no usable rate limit and isn't counted.\n- Inkling 2 Small (40): Memory 0 of 30, the smallest build is Thinking Machines' NVFP4 checkpoint at 393.5 GB, about 472 GB with a fifth added, above the 256 GB line. Runtimes 0, no released version of the six runs it; vLLM and SGLang serve it from their own images and Transformers has it on its main branch only. Builds 15, two precisions from the publisher (NVFP4 and MXFP8). Terms 10, Apache 2.0 with a binding acceptable use policy on top, read as a custom licence. Download 10, no gate. Hosted 5, Thinking Machines' own Tinker serves it as beta serverless inference, and Together is live on Hugging Face. 0 + 0 + 15 + 10 + 10 + 5 = 40.\n\n### Documentation and upkeep: Inkling 2 Small +25\n\n- gpt-oss-20b (42): The model card earns 17, covering six of the seven points and missing a statement of supported languages. Training data earns 10, a general description with a June 2024 cut-off and no sources or mix. Last change earns 5, because the files haven't changed since August 2025 and the reference code and harmony parser last changed on 1 and 5 November 2025, still within a year on 1 November 2026, while this year's commits only touch the browser tool, CI and a version number. Responsiveness earns 0, with no OpenAI reply to any of the 40 most recent discussions and none at all since August 2025. Version policy earns 5 for a first release kept in its own repository. File health earns 5, since template reports and an install report wait without a reply.\n- Inkling 2 Small (67): Model card 17 of 20, everything but a dated knowledge cut-off. Training data 15, an EU training-content summary with sources, mix, an October 2026 collection cut-off and filtering. Last change 20, the files were uploaded on 12 November 2026. Responsiveness 0, the repository has no questions yet, which reads as none answered. Version policy 5, a first release. File health 10, the files agree and no broken-file report waits. 17 + 15 + 20 + 0 + 5 + 10 = 67.\n\n### Risk: gpt-oss-20b +20\n\n- gpt-oss-20b (85): File safety earns 25, since the weights are safetensors and metal/model.bin is OpenAI's own raw Metal format rather than pickle, and nothing in the repository runs as code (a judgement call on the .bin name). Provenance earns 15, files in OpenAI's own organisation and a checksum on every file. Safety evaluation earns 10, because the published safety results for this size are OpenAI's own, and the outside review covered gpt-oss-120b. Agent guidance earns 15 for an instruction hierarchy the model was trained to follow, with prompt-injection results, though OpenAI reports it trails o4-mini there. Licence risk keeps 15, with nothing to deduct under Apache 2.0. The security programme earns 5 for OpenAI's security.txt with a Bugcrowd contact. Public advisories for the gpt-oss code couldn't be checked, so that half scores as absent.\n- Inkling 2 Small (65): File safety 25, safetensors only and no repository code to run. Provenance 15, the files are in the organisation Thinking Machines links to, with a SHA-256 on every LFS file. Safety evaluation 10, Thinking Machines' own StrongREJECT, FORTRESS, HoneyBench and DistressBench results and described outside red-teaming, but nothing an outside party published or a harness to rerun. Agent guidance 5, the card names safeguards to add but doesn't say what its refusals cover, with nothing on prompt injection. Licence risk 5, 10 off for a use policy that reaches beyond the law and that can change at any time. Security programme 5, a security.txt and a disclosure policy, with public advisories unchecked and scored as absent. 25 + 15 + 10 + 5 + 5 + 5 = 65.\n\n### Agent interface: gpt-oss-20b +5\n\n- gpt-oss-20b (90): The chat template earns 20, a Jinja file in the repository. The tool-calling format earns 25, since OpenAI's harmony guide says how functions are declared and how calls come back, and OpenAI ships the openai-harmony parser. Trained tool calling earns 10, because each call ends the message and waits for its result, so it makes one call at a time. Structured output earns 15 for a JSON Schema given in the developer message, documented in the harmony guide. Reasoning control earns 10, with low, medium or high effort per request and the reasoning on its own channel, though it can't be switched off. Context earns 10 for 131,072 tokens, which OpenAI describes as trained in even though the config reaches it with YaRN.\n- Inkling 2 Small (85): Chat template 20, a Jinja file in the repository. Tool-calling format 25, Thinking Machines' tml-renderers guide shows how tools are declared and how calls come back for this model, and its package ships the parser. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, thinking effort is set per request from none to xhigh, and the reasoning comes back in reasoning_content. Context 10, up to 1M tokens. 20 + 25 + 20 + 0 + 10 + 10 = 85.\n\n## Score by category\n\n| Category | Weight | gpt-oss-20b | Inkling 2 Small | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 90 | 40 | gpt-oss-20b +50 |\n| Risk | 20% (20 this run) | 85 | 65 | gpt-oss-20b +20 |\n| Agent interface | 10% (10 this run) | 90 | 85 | gpt-oss-20b +5 |\n| Documentation and upkeep | 10% (10 this run) | 42 | 67 | Inkling 2 Small +25 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **69.9 · B** | **58.8 · C** | |\n\n## Facts side by side\n\n| Fact | gpt-oss-20b | Inkling 2 Small |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | OpenAI | Thinking Machines Lab |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports |  |  |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2025-08-26 | 2026-11-12 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | 3.5/5 (4) | none |\n\n## How the scores have moved\n\n### gpt-oss-20b\n\nNo score change since it was listed.\n\n### Inkling 2 Small\n\n- +6.7 on 12 November 2026 (D to C): product\n\n## Verdicts\n\n**gpt-oss-20b.** gpt-oss-20b is a cousin for reasoning, coding and single tool calls with structured output, under plain Apache 2.0. It needs about 17 GB with a working context, and five inference providers serve it. The main risks are that it trails o4-mini at keeping system instructions above user ones, and OpenAI hasn't answered a report since August 2025.\n\n**Inkling 2 Small.** Thinking Machines' newest open model, a 594B mixture-of-experts generalist with images in, several tool calls a turn and per-request thinking effort. The NVFP4 checkpoint needs about 472 GB, and no released runtime runs it yet, so today that means vLLM's or SGLang's own images, or Tinker and Together hosted. The use policy binds on download and can change.\n\n## Before you call either\n\n### gpt-oss-20b\n\n1. Start it with `ollama run gpt-oss:20b` (the build that fits the reference machine), or `vllm serve openai/gpt-oss-20b` with a current vLLM release rather than the card's pinned vllm==0.10.1+gptoss wheel\n2. Use the harmony format through the chat template or openai-harmony; OpenAI says the model doesn't work correctly without it\n3. Parse tool calls and reasoning with openai-harmony; calls come on the commentary channel ending in `\u003c|call|\u003e`, reasoning on the analysis channel\n4. Set effort with `Reasoning: high` (or low, medium) in the system message, or `reasoning_effort` in the template; medium is the default\n5. Ask for JSON by putting a JSON Schema under `# Response Formats` in the developer message\n6. Drop earlier reasoning after a final answer but pass it back after tool calls, and don't show the analysis channel to users\n7. Expect one tool call per turn; run several in sequence rather than in parallel\n\n### Inkling 2 Small\n\n1. No released runtime runs it yet. Serve the NVFP4 checkpoint from SGLang's dev-inkling-2-small image with the cookbook's recipe for your hardware, or from vLLM's vllm/vllm-openai:inkling-2-small image\n2. In vLLM pass `--reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling`. In SGLang the tool-call parser is `inkling2` and the reasoning parser `inkling`\n3. Transformers' main branch loads only thinkingmachines/Inkling-2-Small-MXFP8, the 622.8 GB checkpoint, and no release has the code yet\n4. Pass `reasoning_effort` as none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99\n5. Effort none conditions the model toward no reasoning but doesn't forbid it, and higher effort needs a larger max_tokens\n6. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error\n7. Images should be 40 to 4096 px a side. The model takes no audio, and the template raises an error for an audio part\n8. Use guided decoding or validate JSON yourself, since structured output isn't documented\n9. Without the hardware, call it on Tinker's OpenAI-compatible endpoint with a Tinker key, at $0.30 input and $1.00 output per million tokens as read on 6 November 2026\n10. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal\n\n## Questions\n\n### Which is better for AI agents, gpt-oss-20b or Inkling 2 Small?\n\ngpt-oss-20b scores 69.9 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 3 of 4 scored categories. Inkling 2 Small leads on documentation and upkeep.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gpt-oss-20b\", \"b\": \"inkling-2-small\"}`. From a terminal: `anchor compare gpt-oss-20b inkling-2-small`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gpt-oss-20b.json and https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json\n\n## Other comparisons with gpt-oss-20b or Inkling 2 Small\n\n- [Agents-A1-4B vs gpt-oss-20b](https://www.anchorterminal.com/compare/agents-a1-4b-vs-gpt-oss-20b.md)\n- [Agents-A1-4B vs Inkling 2 Small](https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling-2-small.md)\n- [Apertus v1.5 8B vs gpt-oss-20b](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-gpt-oss-20b.md)\n- [Apertus v1.5 8B vs Inkling 2 Small](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling-2-small.md)\n- [Apodex-1.1-mini vs gpt-oss-20b](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-gpt-oss-20b.md)\n- [Apodex-1.1-mini vs Inkling 2 Small](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling-2-small.md)\n- [Arete-27B vs gpt-oss-20b](https://www.anchorterminal.com/compare/arete-27b-vs-gpt-oss-20b.md)\n- [Arete-27B vs Inkling 2 Small](https://www.anchorterminal.com/compare/arete-27b-vs-inkling-2-small.md)\n- [BigBang-v1 vs gpt-oss-20b](https://www.anchorterminal.com/compare/bigbang-v1-vs-gpt-oss-20b.md)\n- [BigBang-v1 vs Inkling 2 Small](https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling-2-small.md)\n- [Carbon-X vs gpt-oss-20b](https://www.anchorterminal.com/compare/carbon-x-vs-gpt-oss-20b.md)\n- [Carbon-X vs Inkling 2 Small](https://www.anchorterminal.com/compare/carbon-x-vs-inkling-2-small.md)\n- [Cola2 vs gpt-oss-20b](https://www.anchorterminal.com/compare/cola2-vs-gpt-oss-20b.md)\n- [Cola2 vs Inkling 2 Small](https://www.anchorterminal.com/compare/cola2-vs-inkling-2-small.md)\n- [Cosmos-Reason2-2B vs gpt-oss-20b](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-gpt-oss-20b.md)\n- [Cosmos-Reason2-2B vs Inkling 2 Small](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling-2-small.md)\n- [Darwin-36B-Opus vs gpt-oss-20b](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-gpt-oss-20b.md)\n- [Darwin-36B-Opus vs Inkling 2 Small](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling-2-small.md)\n- [DeepSeek-V3.2 vs gpt-oss-20b](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gpt-oss-20b.md)\n- [DeepSeek-V3.2 vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-2-small.md)\n- [DeepSeek V4.1 Flash vs gpt-oss-20b](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-gpt-oss-20b.md)\n- [DeepSeek V4.1 Flash vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling-2-small.md)\n- [DeepSeek-V4-Flash-0731 vs gpt-oss-20b](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-gpt-oss-20b.md)\n- [DeepSeek-V4-Flash-0731 vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling-2-small.md)\n- [Devstral Small 2 vs gpt-oss-20b](https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-20b.md)\n- [Devstral Small 2 vs Inkling 2 Small](https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-2-small.md)\n- [DiffusionGemma 26B A4B IT vs gpt-oss-20b](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-gpt-oss-20b.md)\n- [DiffusionGemma 26B A4B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-2-small.md)\n- [EXAONE 4.5 33B vs gpt-oss-20b](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-gpt-oss-20b.md)\n- [EXAONE 4.5 33B vs Inkling 2 Small](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-inkling-2-small.md)\n- [Gemma 4 12B IT vs gpt-oss-20b](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-gpt-oss-20b.md)\n- [Gemma 4 12B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling-2-small.md)\n- [Gemma 4 26B A4B IT vs gpt-oss-20b](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-gpt-oss-20b.md)\n- [Gemma 4 26B A4B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling-2-small.md)\n- [Gemma 4 31B IT vs gpt-oss-20b](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-gpt-oss-20b.md)\n- [Gemma 4 31B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling-2-small.md)\n- [Gemma 4 E2B IT vs gpt-oss-20b](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-gpt-oss-20b.md)\n- [Gemma 4 E2B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling-2-small.md)\n- [Gemma 4 E4B IT vs gpt-oss-20b](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-gpt-oss-20b.md)\n- [Gemma 4 E4B IT vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling-2-small.md)\n- [GLM-4.5-Air vs gpt-oss-20b](https://www.anchorterminal.com/compare/glm-4-5-air-vs-gpt-oss-20b.md)\n- [GLM-4.5-Air vs Inkling 2 Small](https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling-2-small.md)\n- [GLM-4.7-Flash vs gpt-oss-20b](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-gpt-oss-20b.md)\n- [GLM-4.7-Flash vs Inkling 2 Small](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling-2-small.md)\n- [GLM-5.3-Flash vs gpt-oss-20b](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-gpt-oss-20b.md)\n- [GLM-5.3-Flash vs Inkling 2 Small](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-2-small.md)\n- [GLM-5.3 vs gpt-oss-20b](https://www.anchorterminal.com/compare/glm-5-3-vs-gpt-oss-20b.md)\n- [GLM-5.3 vs Inkling 2 Small](https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-2-small.md)\n- [gpt-oss-120b vs gpt-oss-20b](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-gpt-oss-20b.md)\n- [gpt-oss-120b vs Inkling 2 Small](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling-2-small.md)\n- [gpt-oss-20b vs Granite 4.2 30B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-granite-4-2-30b.md)\n- [gpt-oss-20b vs Granite 4.2 3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-granite-4-2-3b.md)\n- [gpt-oss-20b vs Granite 4.2 8B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-granite-4-2-8b.md)\n- [gpt-oss-20b vs Hy-Memory-30B-A3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy-memory-30b-a3b.md)\n- [gpt-oss-20b vs Hy3](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy3.md)\n- [gpt-oss-20b vs Inkling](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling.md)\n- [gpt-oss-20b vs Inkling-Small](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-small.md)\n- [gpt-oss-20b vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [gpt-oss-20b vs Kimi K3](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kimi-k3.md)\n- [gpt-oss-20b vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kimi-k3-1-pro.md)\n- [gpt-oss-20b vs Kolibri-1](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kolibri-1.md)\n- [gpt-oss-20b vs Kronos](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-kronos.md)\n- [gpt-oss-20b vs Laguna M.1](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-laguna-m-1.md)\n- [gpt-oss-20b vs Laguna S 2.1](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-laguna-s-2-1.md)\n- [gpt-oss-20b vs Laguna XS 2.1](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-laguna-xs-2-1.md)\n- [gpt-oss-20b vs LBS-27B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lbs-27b.md)\n- [gpt-oss-20b vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm2-5-2-6b.md)\n- [gpt-oss-20b vs LFM3-1.7B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-1-7b.md)\n- [gpt-oss-20b vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-audio-2b.md)\n- [gpt-oss-20b vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-omni-2b.md)\n- [gpt-oss-20b vs LFM3-VL-2B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-vl-2b.md)\n- [gpt-oss-20b vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ling-3-0-tiny.md)\n- [gpt-oss-20b vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ling-3-1-flash-1019.md)\n- [gpt-oss-20b vs LongCat-2.5](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-longcat-2-5.md)\n- [gpt-oss-20b vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-mimo-v2-6-distill-qwen-9b.md)\n- [gpt-oss-20b vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-mimo-v2-6-flash-rl.md)\n- [gpt-oss-20b vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-o-4-5.md)\n- [gpt-oss-20b vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-v-4-7-1b.md)\n- [gpt-oss-20b vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm-v-4-7-35b-a3b.md)\n- [gpt-oss-20b vs MiniCPM5-2B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minicpm5-2b.md)\n- [gpt-oss-20b vs MiniMax-M2.5](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minimax-m2-5.md)\n- [gpt-oss-20b vs MiniMax-M2.7](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minimax-m2-7.md)\n- [gpt-oss-20b vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-minimax-m3-1-flash.md)\n- [gpt-oss-20b vs Mistral Large 4](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-mistral-large-4.md)\n- [gpt-oss-20b vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-muse-glimmer-30b.md)\n- [gpt-oss-20b vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nanbeige-4-2-3b.md)\n- [gpt-oss-20b vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nanbeige-4-3-33b.md)\n- [gpt-oss-20b vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [gpt-oss-20b vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [gpt-oss-20b vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-nano-30b-a3b.md)\n- [gpt-oss-20b vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-nano-4b.md)\n- [gpt-oss-20b vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [gpt-oss-20b vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-super-120b-a12b.md)\n- [gpt-oss-20b vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nemotron-3-ultra-550b-a55b.md)\n- [gpt-oss-20b vs North Mini Code 1.0](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-north-mini-code-1-0.md)\n- [gpt-oss-20b vs occamy-1.0](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-occamy-1-0.md)\n- [gpt-oss-20b vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-olmo-3-7b-think.md)\n- [gpt-oss-20b vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-122b.md)\n- [gpt-oss-20b vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-35b-a3b.md)\n- [gpt-oss-20b vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-397b.md)\n- [gpt-oss-20b vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ornith-1-5-9b.md)\n- [gpt-oss-20b vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-otel-2-0-llm-31b-it.md)\n- [gpt-oss-20b vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen-agentworld-35b-a3b.md)\n- [gpt-oss-20b vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-30b-a3b-instruct-2507.md)\n- [gpt-oss-20b vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-4b-instruct-2507.md)\n- [gpt-oss-20b vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-0-8b.md)\n- [gpt-oss-20b vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-122b-a10b.md)\n- [gpt-oss-20b vs Qwen3.5-2B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-2b.md)\n- [gpt-oss-20b vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-397b-a17b.md)\n- [gpt-oss-20b vs Qwen3.5-4B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-4b.md)\n- [gpt-oss-20b vs Qwen3.5-9B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-5-9b.md)\n- [gpt-oss-20b vs Qwen3.6-27B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-6-27b.md)\n- [gpt-oss-20b vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-6-35b-a3b.md)\n- [gpt-oss-20b vs Qwen3.8-27B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-8-27b.md)\n- [gpt-oss-20b vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-8-flash-next.md)\n- [gpt-oss-20b vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-coder-30b-a3b-instruct.md)\n- [gpt-oss-20b vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-coder-next.md)\n- [gpt-oss-20b vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-omni-30b-a3b-instruct.md)\n- [gpt-oss-20b vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-2b-instruct.md)\n- [gpt-oss-20b vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-30b-a3b-instruct.md)\n- [gpt-oss-20b vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-32b-instruct.md)\n- [gpt-oss-20b vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-4b-instruct.md)\n- [gpt-oss-20b vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwen3-vl-8b-instruct.md)\n- [gpt-oss-20b vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-qwopus3-8-27b-flash-v2.md)\n- [gpt-oss-20b vs Recursive Flint](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-recursive-flint.md)\n- [gpt-oss-20b vs Ripple-65B Preview](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-ripple-65b-preview.md)\n- [gpt-oss-20b vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-sensenova-loop-9b-preview.md)\n- [gpt-oss-20b vs SmolLM3-3B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-smollm3-3b.md)\n- [gpt-oss-20b vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-spark-x2-6-4b.md)\n- [gpt-oss-20b vs Step 3.7 Flash](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-step-3-7-flash.md)\n- [gpt-oss-20b vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-swift-1-5-qwen3-8-27b.md)\n- [gpt-oss-20b vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-swift-1-5-qwen3-8-flash-next.md)\n- [gpt-oss-20b vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-thinkingcap-qwen3-8-27b.md)\n- [gpt-oss-20b vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-unlimited-ocr-2.md)\n- [gpt-oss-20b vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-wevisone-vl-2b.md)\n- [gpt-oss-20b vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-wevisone-vl-4b.md)\n- [gpt-oss-20b vs ZAYA1-8B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-zaya1-8b.md)\n- [Granite 4.2 30B vs Inkling 2 Small](https://www.anchorterminal.com/compare/granite-4-2-30b-vs-inkling-2-small.md)\n- [Granite 4.2 3B vs Inkling 2 Small](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-2-small.md)\n- [Granite 4.2 8B vs Inkling 2 Small](https://www.anchorterminal.com/compare/granite-4-2-8b-vs-inkling-2-small.md)\n- [Hy-Memory-30B-A3B vs Inkling 2 Small](https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-inkling-2-small.md)\n- [Hy3 vs Inkling 2 Small](https://www.anchorterminal.com/compare/hy3-vs-inkling-2-small.md)\n- [Inkling 2 Small vs Inkling-Small](https://www.anchorterminal.com/compare/inkling-2-small-vs-inkling-small.md)\n- [Inkling 2 Small vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/inkling-2-small-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [Inkling 2 Small vs Kimi K3](https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3.md)\n- [Inkling 2 Small vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3-1-pro.md)\n- [Inkling 2 Small vs Kolibri-1](https://www.anchorterminal.com/compare/inkling-2-small-vs-kolibri-1.md)\n- [Inkling 2 Small vs Kronos](https://www.anchorterminal.com/compare/inkling-2-small-vs-kronos.md)\n- [Inkling 2 Small vs Laguna M.1](https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-m-1.md)\n- [Inkling 2 Small vs Laguna S 2.1](https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-s-2-1.md)\n- [Inkling 2 Small vs Laguna XS 2.1](https://www.anchorterminal.com/compare/inkling-2-small-vs-laguna-xs-2-1.md)\n- [Inkling 2 Small vs LBS-27B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lbs-27b.md)\n- [Inkling 2 Small vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm2-5-2-6b.md)\n- [Inkling 2 Small vs LFM3-1.7B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-1-7b.md)\n- [Inkling 2 Small vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-audio-2b.md)\n- [Inkling 2 Small vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-omni-2b.md)\n- [Inkling 2 Small vs LFM3-VL-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-lfm3-vl-2b.md)\n- [Inkling 2 Small vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-0-tiny.md)\n- [Inkling 2 Small vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/inkling-2-small-vs-ling-3-1-flash-1019.md)\n- [Inkling 2 Small vs LongCat-2.5](https://www.anchorterminal.com/compare/inkling-2-small-vs-longcat-2-5.md)\n- [Inkling 2 Small vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Inkling 2 Small vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/inkling-2-small-vs-mimo-v2-6-flash-rl.md)\n- [Inkling 2 Small vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-o-4-5.md)\n- [Inkling 2 Small vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-1b.md)\n- [Inkling 2 Small vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm-v-4-7-35b-a3b.md)\n- [Inkling 2 Small vs MiniCPM5-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-minicpm5-2b.md)\n- [Inkling 2 Small vs MiniMax-M2.5](https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-5.md)\n- [Inkling 2 Small vs MiniMax-M2.7](https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m2-7.md)\n- [Inkling 2 Small vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-m3-1-flash.md)\n- [Inkling 2 Small vs Mistral Large 4](https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-large-4.md)\n- [Inkling 2 Small vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-glimmer-30b.md)\n- [Inkling 2 Small vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-2-3b.md)\n- [Inkling 2 Small vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nanbeige-4-3-33b.md)\n- [Inkling 2 Small vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Inkling 2 Small vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Inkling 2 Small vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-30b-a3b.md)\n- [Inkling 2 Small vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-4b.md)\n- [Inkling 2 Small vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Inkling 2 Small vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-super-120b-a12b.md)\n- [Inkling 2 Small vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-ultra-550b-a55b.md)\n- [Inkling 2 Small vs North Mini Code 1.0](https://www.anchorterminal.com/compare/inkling-2-small-vs-north-mini-code-1-0.md)\n- [Inkling 2 Small vs occamy-1.0](https://www.anchorterminal.com/compare/inkling-2-small-vs-occamy-1-0.md)\n- [Inkling 2 Small vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/inkling-2-small-vs-olmo-3-7b-think.md)\n- [Inkling 2 Small vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-122b.md)\n- [Inkling 2 Small vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-35b-a3b.md)\n- [Inkling 2 Small vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-397b.md)\n- [Inkling 2 Small vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/inkling-2-small-vs-ornith-1-5-9b.md)\n- [Inkling 2 Small vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/inkling-2-small-vs-otel-2-0-llm-31b-it.md)\n- [Inkling 2 Small vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen-agentworld-35b-a3b.md)\n- [Inkling 2 Small vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Inkling 2 Small vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-4b-instruct-2507.md)\n- [Inkling 2 Small vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-0-8b.md)\n- [Inkling 2 Small vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-122b-a10b.md)\n- [Inkling 2 Small vs Qwen3.5-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-2b.md)\n- [Inkling 2 Small vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-397b-a17b.md)\n- [Inkling 2 Small vs Qwen3.5-4B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-4b.md)\n- [Inkling 2 Small vs Qwen3.5-9B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-5-9b.md)\n- [Inkling 2 Small vs Qwen3.6-27B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-27b.md)\n- [Inkling 2 Small vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-6-35b-a3b.md)\n- [Inkling 2 Small vs Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-27b.md)\n- [Inkling 2 Small vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-8-flash-next.md)\n- [Inkling 2 Small vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Inkling 2 Small vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-coder-next.md)\n- [Inkling 2 Small vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-2b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-32b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-4b-instruct.md)\n- [Inkling 2 Small vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwen3-vl-8b-instruct.md)\n- [Inkling 2 Small vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/inkling-2-small-vs-qwopus3-8-27b-flash-v2.md)\n- [Inkling 2 Small vs Recursive Flint](https://www.anchorterminal.com/compare/inkling-2-small-vs-recursive-flint.md)\n- [Inkling 2 Small vs Ripple-65B Preview](https://www.anchorterminal.com/compare/inkling-2-small-vs-ripple-65b-preview.md)\n- [Inkling 2 Small vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/inkling-2-small-vs-sensenova-loop-9b-preview.md)\n- [Inkling 2 Small vs SmolLM3-3B](https://www.anchorterminal.com/compare/inkling-2-small-vs-smollm3-3b.md)\n- [Inkling 2 Small vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/inkling-2-small-vs-spark-x2-6-4b.md)\n- [Inkling 2 Small vs Step 3.7 Flash](https://www.anchorterminal.com/compare/inkling-2-small-vs-step-3-7-flash.md)\n- [Inkling 2 Small vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-27b.md)\n- [Inkling 2 Small vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-2-small-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Inkling 2 Small vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/inkling-2-small-vs-thinkingcap-qwen3-8-27b.md)\n- [Inkling 2 Small vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/inkling-2-small-vs-unlimited-ocr-2.md)\n- [Inkling 2 Small vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-2b.md)\n- [Inkling 2 Small vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/inkling-2-small-vs-wevisone-vl-4b.md)\n- [Inkling 2 Small vs ZAYA1-8B](https://www.anchorterminal.com/compare/inkling-2-small-vs-zaya1-8b.md)\n- [Inkling vs Inkling 2 Small](https://www.anchorterminal.com/compare/inkling-vs-inkling-2-small.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-15",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "gpt-oss-20b vs Inkling 2 Small",
        "url": ""
      }
    ],
    "description": "gpt-oss-20b scores 69.9 (B) to Inkling 2 Small's 58.8 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "gpt-oss-20b B 69.9",
      "Inkling 2 Small C 58.8",
      "scores"
    ],
    "h1": "gpt-oss-20b vs Inkling 2 Small",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/gpt-oss-20b-vs-inkling-2-small",
    "published": "2026-10-01",
    "section": "tools",
    "title": "gpt-oss-20b vs Inkling 2 Small for AI agents (2026) | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-12",
    "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-2-small"
  },
  "tokens": {
    "markdown": 9800,
    "slim": 730
  },
  "version": 1
}