{ "data": { "a": { "slug": "devstral-small-2", "name": "Devstral Small 2", "vendor": "Mistral AI", "vendorUrl": "https://mistral.ai", "kind": "weights", "category": "open-weights", "summary": "Devstral Small 2 is Mistral's open-weight coding agent model, 24B parameters with image input, tool calling and a 256K context. Apache 2.0. It runs in vLLM, SGLang, Transformers, llama.cpp and Ollama, where the 4-bit build is 15 GB.", "url": "https://www.anchorterminal.com/tools/devstral-small-2", "markdownUrl": "https://www.anchorterminal.com/tools/devstral-small-2.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/devstral-small-2.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/devstral-small-2.json", "dns": "devstral-small-2.grade.anchorterminal.com", "repo": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "mistralai/Devstral-Small-2-24B-Instruct-2512" }, { "registry": "ollama", "name": "devstral-small-2" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download and use under Apache 2.0. Running it yourself takes 15 GB at Q4_K_M from Ollama's library, 26 GB in FP8 from Mistral, or 26 GB at Q8_0 from ggml-org. Mistral's API serves it too (checked 2026-11-10).", "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 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "coding", "agentic", "vision", "tool-calling", "long-context", "apache-2.0", "safetensors", "fp8", "gguf", "ollama", "self-hosted" ], "lastRelease": "2026-07-15", "graded": true, "anchor": { "graded": true, "score": 61, "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": 1518, "categoryRank": 50, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 65, "reach": 90, "risk": 60, "upkeep": 46 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-10" }, "negative": 0, "verdict": "The easy one to run: a 24B coding agent under Apache 2.0 that five runtimes carry, 15 GB at 4 bits in Ollama, with a 256K context, image input and well-documented tool calling. It's eleven months old, calls tools one at a time, has no reasoning mode, and its card says nothing on limits, safety or data.", "bestFor": "Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac", "strengths": [ "Runs in vLLM, SGLang, Transformers, llama.cpp and Ollama", "15 GB at 4 bits from Ollama's library", "Apache 2.0, ungated, and on Mistral's API", "Tool calling documented, with test prompts and expected output", "A 256K context with image input" ], "weaknesses": [ "No limitations, safety results, languages or data on the card", "No reasoning mode", "Tool calls one at a time, by the card's own tests", "Released in December 2025, and newer coding models have passed it", "Mistral ships FP8 only. The 4-bit builds are other people's" ], "agentNotes": [ "`ollama run devstral-small-2` is the quickest start, at 15 GB", "On vLLM pass `--tool-call-parser mistral --enable-auto-tool-choice`", "Send the system prompt from CHAT_SYSTEM_PROMPT.txt in the repository. The card says results depend on it", "Use a low temperature. The repository's default is 0.15", "Plan for one tool call per turn", "The same model is on our Mistral API listing if you'd rather not host it" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 65, "reach": 90, "risk": 60, "upkeep": 46 }, "provenanceScore": 84, "checked": { "categories": { "interface": "2026-11-10", "reach": "2026-11-10", "risk": "2026-11-10", "upkeep": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "ollama run devstral-small-2\n# or: vllm serve mistralai/Devstral-Small-2-24B-Instruct-2512 --max-model-len 262144 --tool-call-parser mistral --enable-auto-tool-choice", "http": "# vLLM serves an OpenAI-compatible API at http://localhost:8000/v1, and Ollama at http://localhost:11434/v1.\n# Send the system prompt from CHAT_SYSTEM_PROMPT.txt and tools in the OpenAI function format" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/devstral-small-2" }, "sameCompany": [ "mistral-embeddings", "mistral-moderation", "mistral-voxtral-transcribe", "voxtral-mini-4b-realtime-2602", "mistral-ocr", "mistral-vibe-cli", "mistral-large-4" ], "sameModel": [ "mistral-api" ], "weights": { "trainedBy": "Mistral AI", "builtOn": "Mistral-Small-3.1-24B-Base-2503, per the metadata", "params": "24B", "context": 262144, "goodFor": "A coding agent on one 24 GB GPU or a 32 GB Mac: exploring a repository, editing files and calling tools, with screenshots and diagrams as input.", "runtimes": [ "llama.cpp", "Ollama", "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "Ollama devstral-small-2 (Q4_K_M)", "url": "https://ollama.com/library/devstral-small-2", "who": "ollama", "precision": "q4_k_m", "sizeGB": 15, "memoryGB": 24, "format": "ollama", "runsOn": [ "Ollama" ], "note": "From Ollama's own library, 15 GB as its tags page lists it" }, { "name": "Devstral-Small-2-24B-Instruct-2512 (FP8 safetensors)", "url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "who": "publisher", "precision": "fp8", "sizeGB": 25.79, "memoryGB": 32, "format": "safetensors", "runsOn": [ "vLLM", "SGLang", "Transformers" ], "note": "Mistral's release precision. The repository holds it in two layouts" }, { "name": "ggml-org Devstral-Small-2-24B-Instruct-2512-GGUF (Q8_0)", "url": "https://huggingface.co/ggml-org/Devstral-Small-2-24B-Instruct-2512-GGUF", "who": "llama.cpp", "precision": "q8_0", "sizeGB": 25.94, "memoryGB": 32, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "From ggml-org, the llama.cpp project's organisation. 25.06 GB of Q8_0 weights plus the 0.88 GB F16 projector, from the Hub's model information on 10 November 2026" }, { "name": "Ollama devstral-small-2 (Q8_0)", "url": "https://ollama.com/library/devstral-small-2", "who": "ollama", "precision": "q8_0", "sizeGB": 26, "memoryGB": 32, "format": "ollama", "runsOn": [ "Ollama" ], "note": "From Ollama's own library, 26 GB as its tags page lists it" } ], "run": "ollama run devstral-small-2", "runBuild": "Ollama devstral-small-2 (Q4_K_M)", "checked": "2026-11-10", "minMemoryGB": 24 }, "family": { "lab": "Mistral AI", "family": "Devstral", "url": "https://www.anchorterminal.com/open-weights/#mistral", "olderCount": 49 }, "area": "models", "provenance": { "legalEntity": "Mistral AI (RCS Paris 952 418 325)", "domain": "mistral.ai", "domainRegistered": "2019-05-15", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/commits/main", "securityTxt": "valid", "checked": "2026-11-10", "notes": [ "The files sit in Mistral's verified mistralai organisation. Legal entity, domain and security.txt are carried from our Mistral Large 4 listing.", "Nothing is hosted under this listing, so Apache 2.0 stands in for terms of service and no privacy policy is scored. The Mistral API that serves this model has its own listing.", "The changelog is the commit history, 25 commits from 9 December 2025 to 15 July 2026." ], "score": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/devstral-small-2.json" }, "answer": "GLM-5.3 scores 64.6 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk.", "b": { "slug": "glm-5-3", "name": "GLM-5.3", "vendor": "Z.ai (Zhipu AI)", "vendorUrl": "https://z.ai", "kind": "weights", "category": "open-weights", "summary": "GLM-5.3 is Z.ai's open-weight mixture-of-experts model for coding and long-horizon agent work, 744B parameters with 40B active and a 1M-token context, published on Hugging Face in FP8 and BF16 under its own licence.", "url": "https://www.anchorterminal.com/tools/glm-5-3", "markdownUrl": "https://www.anchorterminal.com/tools/glm-5-3.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/glm-5-3.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/glm-5-3.json", "dns": "glm-5-3.grade.anchorterminal.com", "repo": "https://huggingface.co/zai-org/GLM-5.3", "license": "GLM-5.3 License (MIT-style, with a security review for the largest model-as-a-service operators)", "transports": [], "packages": [ { "registry": "huggingface", "name": "zai-org/GLM-5.3" }, { "registry": "huggingface", "name": "zai-org/GLM-5.3-BF16" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither repository is gated (checked 2026-10-21).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under the GLM-5.3 License. A licensee running a model-as-a-service business with more than US$10 billion of revenue in 12 months must pass Z.AI's security review before commercial use. Running it yourself costs the hardware, 755.7 GB of FP8 files (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": "2026-11-02" }, "docsUrl": "https://huggingface.co/zai-org/GLM-5.3", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "reasoning", "tool-calling", "coding", "long-context", "custom-licence", "safetensors", "fp8", "self-hosted" ], "lastRelease": "2026-10-15", "graded": true, "anchor": { "graded": true, "score": 64.6, "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": 1518, "categoryRank": 16, "methodology": "0.7", "run": "2026-10-01", "scores": { "capability": 80, "interface": 70, "reach": 55, "risk": 50, "upkeep": 58 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-11-02" }, "negative": 0, "verdict": "A large coding and long-horizon agent model with a 1M-token context, several tool calls per turn and three reasoning budgets. Z.ai's smallest build is 756 GB in FP8, so it needs an 8-GPU server, Z.ai's API or a provider. The main risks are no published safety work, no way to report a flaw, and thinking that can't be turned off.", "bestFor": "Teams with an 8-GPU server who want an open coding and long-horizon agent model with a 1M-token context, or agents that call it through Z.ai or a hosted provider", "strengths": [ "Model code in released llama.cpp b11768, vLLM 0.28.0, SGLang 0.5.22 and Transformers 5.12.0", "1,048,576 tokens of native context and three reasoning budgets per request", "Template renders several tool calls per turn, parsed by glm47 in vLLM and SGLang", "Safetensors only, no remote code, files in Z.ai's own organisation with a SHA-256 per shard", "Downloadable with no account, and hosted by Z.ai and eight live providers on Hugging Face" ], "weaknesses": [ "Z.ai's smallest build is 755.6 GB in FP8, with no local Ollama or LM Studio build", "No safety evaluation, agent-use guidance or security contact", "Thinking is always on, and reasoning_effort only lowers it", "Commercial use by model-as-a-service operators above US$10 billion revenue needs Z.AI's security review", "The card leaves out limitations, architecture, parameters and cut-off, and zai-org answered 2 of 16 discussions, none since 8 September" ], "agentNotes": [ "Start it with `vllm serve zai-org/GLM-5.3 --kv-cache-dtype fp8 --tensor-parallel-size 8 --speculative-config.method mtp --speculative-config.num_speculative_tokens 5 --tool-call-parser glm47 --reasoning-parser glm47 --enable-auto-tool-choice --served-model-name glm-5.3` (vLLM 0.28.0 or later, 8xH200 or 8xH20 per vLLM's recipe)", "Use the glm47 tool-call and reasoning parsers in vLLM or SGLang; SGLang's cookbook says glm45 leaves the calls as plain text", "Pass `chat_template_kwargs: {\"reasoning_effort\": \"low\"}` for short tasks; anything other than low or high falls back to max", "Pass `clear_thinking: true` in chat use, since the template keeps earlier reasoning by default", "Don't send `enable_thinking: false`; the template ignores it and always opens a think block", "Validate JSON output yourself, since structured output is documented only for Z.ai's hosted API", "No Z.ai build fits a 128 GB machine; the full 1M context needs 8xB200 per vLLM's recipe" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.6 } ], "editorialScores": { "capability": 80, "interface": 70, "reach": 55, "risk": 50, "upkeep": 58 }, "provenanceScore": 73, "checked": { "categories": { "capability": "2026-11-02", "interface": "2026-11-02", "reach": "2026-11-02", "risk": "2026-11-02", "upkeep": "2026-11-02" }, "last": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# vLLM's recipe, FP8 on one 8xH200 node\nuv pip install \"vllm\u003e=0.28.0\" --torch-backend=auto\nvllm serve zai-org/GLM-5.3 --kv-cache-dtype fp8 --tensor-parallel-size 8 \\\n --speculative-config.method mtp --speculative-config.num_speculative_tokens 5 \\\n --tool-call-parser glm47 --reasoning-parser glm47 --enable-auto-tool-choice \\\n --served-model-name glm-5.3\n# or, with llama.cpp and Unsloth's GGUF, a third party's conversion:\nllama-server -hf unsloth/GLM-5.3-GGUF:UD-Q4_K_XL --jinja", "http": "curl http://localhost:8000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"glm-5.3\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n \"chat_template_kwargs\": {\"reasoning_effort\": \"low\", \"clear_thinking\": true}\n }'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/glm-5-3" }, "sameCompany": [ "glm-4-5-air", "glm-4-7-flash", "glm-5-3-flash" ], "weights": { "trainedBy": "Z.ai", "builtOn": "GLM-5.2's base model (same base, new post-training)", "params": "744B", "active": "40B", "context": 1048576, "goodFor": "Large model for coding and long-horizon agent work with tool calling and always-on reasoning, text only.", "runtimes": [ "llama.cpp", "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "GLM-5.3", "url": "https://huggingface.co/zai-org/GLM-5.3", "who": "publisher", "precision": "fp8", "sizeGB": 755.6, "memoryGB": 1024, "format": "safetensors" }, { "name": "unsloth GLM-5.3-GGUF (UD-Q4_K_XL)", "url": "https://huggingface.co/unsloth/GLM-5.3-GGUF", "who": "unsloth", "precision": "q4_k_xl", "sizeGB": 467.29, "memoryGB": 1024, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "From Unsloth, a third party's conversion and not Z.ai's. 467.29 GB of UD-Q4_K_XL weights, from the Hub's model information on 10 November 2026. Recorded after the last grading, so Reach doesn't count it" }, { "name": "GLM-5.3-BF16", "url": "https://huggingface.co/zai-org/GLM-5.3-BF16", "who": "publisher", "precision": "bf16", "sizeGB": 1506.7, "memoryGB": 2048, "format": "safetensors", "runsOn": [ "vLLM (ROCm)", "SGLang (ROCm)" ] } ], "run": "vllm serve zai-org/GLM-5.3 --kv-cache-dtype fp8 --tensor-parallel-size 8 --speculative-config.method mtp --speculative-config.num_speculative_tokens 5 --tool-call-parser glm47 --reasoning-parser glm47 --enable-auto-tool-choice --served-model-name glm-5.3", "runBuild": "GLM-5.3", "checked": "2026-10-21", "minMemoryGB": 1024 }, "family": { "lab": "Z.ai (Zhipu AI)", "family": "GLM-5", "url": "https://www.anchorterminal.com/open-weights/#zai", "others": [ { "name": "GLM-5", "url": "https://huggingface.co/zai-org/GLM-5", "params": "744B-A40B" }, { "name": "GLM-5.1", "url": "https://huggingface.co/zai-org/GLM-5.1", "params": "744B-A40B" }, { "name": "GLM-5.2", "url": "https://huggingface.co/zai-org/GLM-5.2", "params": "744B-A40B" }, { "name": "GLM-5.3-Flash", "url": "https://huggingface.co/zai-org/GLM-5.3-Flash", "params": "320B-A18B", "listing": "https://www.anchorterminal.com/tools/glm-5-3-flash" } ], "olderCount": 19, "unrestrictedCopies": 5 }, "area": "models", "provenance": { "legalEntity": "JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai). The licence names Z.AI", "domain": "z.ai", "domainRegistered": "2017-12-15", "domainNote": "z.ai was registered in 2017 and transferred in October 2024, so its age says little about the company's.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/zai-org/GLM-5.3/commits/main", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "Z.ai's terms of use name JINGSHENG HENGXING TECHNOLOGY PTE.LTD as the operator of Z.ai, and RDAP names the same company as the registrant of z.ai. The weights' LICENSE names Z.AI as the copyright holder.", "Nothing is hosted for this listing, so the GLM-5.3 License stands in for terms of service and no privacy policy is scored.", "The changelog is the repository's commit history, 11 commits from 27 August to 14 October 2026, whose messages say what changed (two chat template fixes, on 4 September and 14 October, and evaluation results).", "z.ai/.well-known/security.txt and docs.z.ai/.well-known/security.txt answered 404 on 21 October 2026." ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/glm-5-3.json", "live": { "slug": "glm-5-3", "securityTxt": { "url": "https://z.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-10T16:09:36.154640571Z" }, "domain": { "domain": "z.ai", "registered": "2017-12-15", "source": "https://rdap.identitydigital.services/rdap/domain/z.ai", "checkedAt": "2026-11-08T15:05:18.801433245Z" }, "pages": [ { "url": "https://huggingface.co/zai-org/GLM-5.3/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-11-10T16:24:04.914285738Z", "changedAt": "2026-11-10T16:24:04.914285738Z", "fingerprint": "ff4e45ec78e4" } ], "updatedAt": "2026-11-10T16:24:04.914285738Z" } }, "edges": [ { "by": 35, "category": "reach", "leads": "devstral-small-2", "name": "Reach", "reasons": { "a": "Memory 25, the smallest build at 4 bits from a runtime's own library is Ollama's devstral-small-2 at Q4_K_M, 15 GB, and 15 GB × 1.2 = 18 GB, within 24 GB. Mistral's own FP8 files are 25.79 GB. Runtimes 25, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the mistral3 model, llama.cpp b12242 has the architecture with a GGUF from its own organisation, and Ollama's library has devstral-small-2. Builds 10, one quantised precision from Mistral, the FP8 weights it releases. Terms 15, Apache 2.0 in the card's metadata and text, an OSI licence with nothing added. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Mistral's own API serves Devstral Small 2: the card says the model is available through its API and points there when a local runtime underperforms. 25 + 25 + 10 + 15 + 10 + 5 = 90.", "b": "Memory earns nothing, since Z.ai's smallest build is the 755.6 GB FP8 one, about 907 GB with the fifth added, and Ollama only lists a cloud entry. Four runtimes run it in a released version, llama.cpp, vLLM, SGLang and Transformers, for 20, while Ollama and LM Studio have no local build. Z.ai publishes one quantised build, FP8, for 10, since the BF16 repository is the full precision. The GLM-5.3 License is a custom licence that is free for commercial use below a revenue threshold, for 10. The files download with no account or gate, for 10, and Z.ai's own API plus eight live providers on Hugging Face serve it, for 5." }, "scores": { "a": 90, "b": 55 } }, { "by": 12, "category": "upkeep", "leads": "glm-5-3", "name": "Documentation and upkeep", "reasons": { "a": "Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the last commit, on 15 July 2026, updated the files to match mistral-common, 118 days before this check and within 180. Responsiveness 10, Of the 23 most recent discussions that aren't pull requests (9 December 2025 to 6 November 2026), 11 have a reply from a mistralai member, which is some. Version policy 5, Devstral Small 1.1 stays in its own repository, which this card links as the predecessor, with no dated note on the older card that we read. File health 10, Config, template, tokenizer and card agree, and the June and July commits fixed stray tokens and brought the files in line with mistral-common. 11 + 0 + 10 + 10 + 5 + 10 = 46.", "b": "The card covers intended use, languages and context and misses limitations, architecture, parameters and cut-off, for 8. Training data is 5, a description of the GLM-5 corpus in the cited report with no cut-off. The last change, a chat template speed-up on 14 October in the FP8 repository and on 15 October in the BF16 one, is within 30 days on 2 November, for 20. Responsiveness is 5, as zai-org answered 2 of the 16 discussions that aren't pull requests, the last on 8 September, which is a few, and no discussion has been opened since 10 October. Version policy is the full 10, with each GLM-5 release in its own repository and a dated blog saying what changed from GLM-5.2. File health is the full 10, with files and card agreeing and no broken-file report waiting by title." }, "scores": { "a": 46, "b": 58 } }, { "by": 10, "category": "risk", "leads": "devstral-small-2", "name": "Risk", "reasons": { "a": "File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, files in Mistral's verified mistralai organisation, which Mistral's site links to per our Mistral Large 4 listing (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 5, mistral.ai's security.txt gives a security contact and a submission policy, as read for the Mistral Large 4 listing (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.", "b": "File safety is full, with safetensors only, no Python in the repository and no remote code needed in Transformers 5.12.0 or later. Provenance is full, files in the zai-org organisation Z.ai links to with a SHA-256 for every shard. Safety evaluation is 0, because the blog mentions safety evaluation and hardening but publishes no results, and agent guidance is 0, with nothing on refusals, prompt injection or cautions. Licence risk is 10, losing 5 for the security review that model-as-a-service operators above US$10 billion of revenue must pass. The security programme is 0, with no security.txt, no SECURITY.md and no advisories." }, "scores": { "a": 60, "b": 50 } }, { "by": 5, "category": "interface", "leads": "glm-5-3", "name": "Agent interface", "reasons": { "a": "Chat template 20, chat_template.jinja in the repository (11,362 characters), with the tokenizer's tekken file for mistral-common. Tool-calling format 25, the card documents tools in the OpenAI function format with an example, names the mistral tool-call parser with auto tool choice for vLLM, shows the same for SGLang, and ships test prompts with the expected tool-call output. Trained tool calling 10, the card says the model excels at using tools, and its tests cover one tool call and calls made one at a time in sequence. Structured output 0, Nothing on the card about JSON or schema-constrained answers for this model. Reasoning control 0, no reasoning mode is documented, and a June 2026 commit removed stray thinking tokens from the files. Context 10, 256K tokens per the card, served at 262,144 in its vLLM command. 20 + 25 + 10 + 0 + 0 + 10 = 65.", "b": "A Jinja chat template sits in the repository, for 20. The tool-calling format is 10, since it is defined only by the template and the glm47 parser is named by vLLM and SGLang rather than by Z.ai. The template takes several calls in one turn, for 20. Structured output is 0, with nothing on the card and JSON documented only for the hosted API. Reasoning control is 10, a per-request budget through reasoning_effort with the reasoning in a think block, though thinking can't be turned off. Context is 10, 1,048,576 tokens native with no rope scaling." }, "scores": { "a": 65, "b": 70 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Mistral AI", "b": "Z.ai (Zhipu AI)", "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": "GLM-5.3 License (MIT-style, with a security review for the largest model-as-a-service operators)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-07-15", "b": "2026-10-15", "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": "none", "b": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "GLM-5.3 scores 64.6 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk.", "question": "Which is better for AI agents, Devstral Small 2 or GLM-5.3?" } ], "goodFor": [ { "aheadOn": [ "Reach, 90 against 55", "Risk, 60 against 50" ], "also": null, "goodFor": "Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac", "slug": "devstral-small-2", "watchFor": "No limitations, safety results, languages or data on the card" }, { "aheadOn": [ "Agent interface, 70 against 65", "Documentation and upkeep, 58 against 46" ], "also": null, "goodFor": "Teams with an 8-GPU server who want an open coding and long-horizon agent model with a 1M-token context, or agents that call it through Z.ai or a hosted provider", "slug": "glm-5-3", "watchFor": "Z.ai's smallest build is 755.6 GB in FP8, with no local Ollama or LM Studio build" } ], "history": null, "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-devstral-small-2.json", "title": "Agents-A1-4B vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-glm-5-3.json", "title": "Agents-A1-4B vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-devstral-small-2.json", "title": "Apertus v1.5 8B vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-glm-5-3.json", "title": "Apertus v1.5 8B vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-devstral-small-2.json", "title": "Apodex-1.1-mini vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-glm-5-3.json", "title": "Apodex-1.1-mini vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-devstral-small-2.json", "title": "Arete-27B vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-glm-5-3.json", "title": "Arete-27B vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-devstral-small-2.json", "title": "BigBang-v1 vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-glm-5-3.json", "title": "BigBang-v1 vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-devstral-small-2.json", "title": "Carbon-X vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3.json", "title": "Carbon-X vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-devstral-small-2.json", "title": "Cola2 vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/cola2-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-glm-5-3.json", "title": "Cola2 vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/cola2-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-devstral-small-2.json", "title": "Cosmos-Reason2-2B vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-glm-5-3.json", "title": "Cosmos-Reason2-2B vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-devstral-small-2.json", "title": "Darwin-36B-Opus vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-glm-5-3.json", "title": "Darwin-36B-Opus vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-devstral-small-2.json", "title": "DeepSeek-V3.2 vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-5-3.json", "title": "DeepSeek-V3.2 vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-devstral-small-2.json", "title": "DeepSeek V4.1 Flash vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-glm-5-3.json", "title": "DeepSeek V4.1 Flash vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-devstral-small-2.json", "title": "DeepSeek-V4-Flash-0731 vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-glm-5-3.json", "title": "DeepSeek-V4-Flash-0731 vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-diffusiongemma-26b-a4b-it.json", "title": "Devstral Small 2 vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-diffusiongemma-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-exaone-4-5-33b.json", "title": "Devstral Small 2 vs EXAONE 4.5 33B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-exaone-4-5-33b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-12b-it.json", "title": "Devstral Small 2 vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-26b-a4b-it.json", "title": "Devstral Small 2 vs Gemma 4 26B A4B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-31b-it.json", "title": "Devstral Small 2 vs Gemma 4 31B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-31b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e2b-it.json", "title": "Devstral Small 2 vs Gemma 4 E2B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e2b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e4b-it.json", "title": "Devstral Small 2 vs Gemma 4 E4B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e4b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-5-air.json", "title": "Devstral Small 2 vs GLM-4.5-Air", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-5-air" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-7-flash.json", "title": "Devstral Small 2 vs GLM-4.7-Flash", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-7-flash" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash.json", "title": "Devstral Small 2 vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-120b.json", "title": "Devstral Small 2 vs gpt-oss-120b", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-120b" }, { "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-granite-4-2-30b.json", "title": "Devstral Small 2 vs Granite 4.2 30B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-30b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-3b.json", "title": "Devstral Small 2 vs Granite 4.2 3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-8b.json", "title": "Devstral Small 2 vs Granite 4.2 8B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-8b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy-memory-30b-a3b.json", "title": "Devstral Small 2 vs Hy-Memory-30B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy-memory-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3.json", "title": "Devstral Small 2 vs Hy3", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling.json", "title": "Devstral Small 2 vs Inkling", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-small.json", "title": "Devstral Small 2 vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "Devstral Small 2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3.json", "title": "Devstral Small 2 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3-1-pro.json", "title": "Devstral Small 2 vs Kimi K3.1 Pro", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3-1-pro" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kolibri-1.json", "title": "Devstral Small 2 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kronos.json", "title": "Devstral Small 2 vs Kronos", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-m-1.json", "title": "Devstral Small 2 vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-s-2-1.json", "title": "Devstral Small 2 vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-xs-2-1.json", "title": "Devstral Small 2 vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lbs-27b.json", "title": "Devstral Small 2 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm2-5-2-6b.json", "title": "Devstral Small 2 vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-1-7b.json", "title": "Devstral Small 2 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-audio-2b.json", "title": "Devstral Small 2 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-omni-2b.json", "title": "Devstral Small 2 vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-vl-2b.json", "title": "Devstral Small 2 vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-0-tiny.json", "title": "Devstral Small 2 vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-1-flash-1019.json", "title": "Devstral Small 2 vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-longcat-2-5.json", "title": "Devstral Small 2 vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Devstral Small 2 vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-flash-rl.json", "title": "Devstral Small 2 vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-o-4-5.json", "title": "Devstral Small 2 vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-1b.json", "title": "Devstral Small 2 vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-35b-a3b.json", "title": "Devstral Small 2 vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm5-2b.json", "title": "Devstral Small 2 vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-5.json", "title": "Devstral Small 2 vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-7.json", "title": "Devstral Small 2 vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m3-1-flash.json", "title": "Devstral Small 2 vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mistral-large-4.json", "title": "Devstral Small 2 vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-muse-glimmer-30b.json", "title": "Devstral Small 2 vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-2-3b.json", "title": "Devstral Small 2 vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-3-33b.json", "title": "Devstral Small 2 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "Devstral Small 2 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Devstral Small 2 vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-30b-a3b.json", "title": "Devstral Small 2 vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-4b.json", "title": "Devstral Small 2 vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Devstral Small 2 vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-super-120b-a12b.json", "title": "Devstral Small 2 vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-ultra-550b-a55b.json", "title": "Devstral Small 2 vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-north-mini-code-1-0.json", "title": "Devstral Small 2 vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-occamy-1-0.json", "title": "Devstral Small 2 vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-olmo-3-7b-think.json", "title": "Devstral Small 2 vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-122b.json", "title": "Devstral Small 2 vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-35b-a3b.json", "title": "Devstral Small 2 vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-397b.json", "title": "Devstral Small 2 vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-9b.json", "title": "Devstral Small 2 vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-otel-2-0-llm-31b-it.json", "title": "Devstral Small 2 vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen-agentworld-35b-a3b.json", "title": "Devstral Small 2 vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Devstral Small 2 vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-4b-instruct-2507.json", "title": "Devstral Small 2 vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-0-8b.json", "title": "Devstral Small 2 vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-122b-a10b.json", "title": "Devstral Small 2 vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-2b.json", "title": "Devstral Small 2 vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-397b-a17b.json", "title": "Devstral Small 2 vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-4b.json", "title": "Devstral Small 2 vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-9b.json", "title": "Devstral Small 2 vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-27b.json", "title": "Devstral Small 2 vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-35b-a3b.json", "title": "Devstral Small 2 vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-27b.json", "title": "Devstral Small 2 vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-flash-next.json", "title": "Devstral Small 2 vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Devstral Small 2 vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-next.json", "title": "Devstral Small 2 vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Devstral Small 2 vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-2b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-32b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-4b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-8b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwopus3-8-27b-flash-v2.json", "title": "Devstral Small 2 vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-recursive-flint.json", "title": "Devstral Small 2 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ripple-65b-preview.json", "title": "Devstral Small 2 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-sensenova-loop-9b-preview.json", "title": "Devstral Small 2 vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-smollm3-3b.json", "title": "Devstral Small 2 vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-spark-x2-6-4b.json", "title": "Devstral Small 2 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-step-3-7-flash.json", "title": "Devstral Small 2 vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-27b.json", "title": "Devstral Small 2 vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Devstral Small 2 vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-thinkingcap-qwen3-8-27b.json", "title": "Devstral Small 2 vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-unlimited-ocr-2.json", "title": "Devstral Small 2 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-2b.json", "title": "Devstral Small 2 vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-4b.json", "title": "Devstral Small 2 vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-zaya1-8b.json", "title": "Devstral Small 2 vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-zaya1-8b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3.json", "title": "DiffusionGemma 26B A4B IT vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-glm-5-3.json", "title": "EXAONE 4.5 33B vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3.json", "title": "Gemma 4 12B IT vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-glm-5-3.json", "title": "Gemma 4 26B A4B IT vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-glm-5-3.json", "title": "Gemma 4 31B IT vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-glm-5-3.json", "title": "Gemma 4 E2B IT vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-glm-5-3.json", "title": "Gemma 4 E4B IT vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-glm-5-3.json", "title": "GLM-4.5-Air vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-glm-5-3.json", "title": "GLM-4.7-Flash vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-glm-5-3-flash.json", "title": "GLM-5.3 vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-gpt-oss-120b.json", "title": "GLM-5.3 vs gpt-oss-120b", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-gpt-oss-120b" }, { "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-granite-4-2-30b.json", "title": "GLM-5.3 vs Granite 4.2 30B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-granite-4-2-30b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-granite-4-2-3b.json", "title": "GLM-5.3 vs Granite 4.2 3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-granite-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-granite-4-2-8b.json", "title": "GLM-5.3 vs Granite 4.2 8B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-granite-4-2-8b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-hy-memory-30b-a3b.json", "title": "GLM-5.3 vs Hy-Memory-30B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-hy-memory-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-hy3.json", "title": "GLM-5.3 vs Hy3", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling.json", "title": "GLM-5.3 vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-small.json", "title": "GLM-5.3 vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "GLM-5.3 vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-kimi-k3.json", "title": "GLM-5.3 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-kimi-k3-1-pro.json", "title": "GLM-5.3 vs Kimi K3.1 Pro", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-kimi-k3-1-pro" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-kolibri-1.json", "title": "GLM-5.3 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-kronos.json", "title": "GLM-5.3 vs Kronos", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-laguna-m-1.json", "title": "GLM-5.3 vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-laguna-s-2-1.json", "title": "GLM-5.3 vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-laguna-xs-2-1.json", "title": "GLM-5.3 vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-lbs-27b.json", "title": "GLM-5.3 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm2-5-2-6b.json", "title": "GLM-5.3 vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-1-7b.json", "title": "GLM-5.3 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-audio-2b.json", "title": "GLM-5.3 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-omni-2b.json", "title": "GLM-5.3 vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-vl-2b.json", "title": "GLM-5.3 vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-ling-3-0-tiny.json", "title": "GLM-5.3 vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-ling-3-1-flash-1019.json", "title": "GLM-5.3 vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-longcat-2-5.json", "title": "GLM-5.3 vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-mimo-v2-6-distill-qwen-9b.json", "title": "GLM-5.3 vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-mimo-v2-6-flash-rl.json", "title": "GLM-5.3 vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm-o-4-5.json", "title": "GLM-5.3 vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm-v-4-7-1b.json", "title": "GLM-5.3 vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm-v-4-7-35b-a3b.json", "title": "GLM-5.3 vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm5-2b.json", "title": "GLM-5.3 vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-minimax-m2-5.json", "title": "GLM-5.3 vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-minimax-m2-7.json", "title": "GLM-5.3 vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-minimax-m3-1-flash.json", "title": "GLM-5.3 vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-mistral-large-4.json", "title": "GLM-5.3 vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-muse-glimmer-30b.json", "title": "GLM-5.3 vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nanbeige-4-2-3b.json", "title": "GLM-5.3 vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nanbeige-4-3-33b.json", "title": "GLM-5.3 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "GLM-5.3 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "GLM-5.3 vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-nano-30b-a3b.json", "title": "GLM-5.3 vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-nano-4b.json", "title": "GLM-5.3 vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "GLM-5.3 vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-super-120b-a12b.json", "title": "GLM-5.3 vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-ultra-550b-a55b.json", "title": "GLM-5.3 vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-north-mini-code-1-0.json", "title": "GLM-5.3 vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-occamy-1-0.json", "title": "GLM-5.3 vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-olmo-3-7b-think.json", "title": "GLM-5.3 vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-122b.json", "title": "GLM-5.3 vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-35b-a3b.json", "title": "GLM-5.3 vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-397b.json", "title": "GLM-5.3 vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-9b.json", "title": "GLM-5.3 vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-otel-2-0-llm-31b-it.json", "title": "GLM-5.3 vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen-agentworld-35b-a3b.json", "title": "GLM-5.3 vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-30b-a3b-instruct-2507.json", "title": "GLM-5.3 vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-4b-instruct-2507.json", "title": "GLM-5.3 vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-0-8b.json", "title": "GLM-5.3 vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-122b-a10b.json", "title": "GLM-5.3 vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-2b.json", "title": "GLM-5.3 vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-397b-a17b.json", "title": "GLM-5.3 vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-4b.json", "title": "GLM-5.3 vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-9b.json", "title": "GLM-5.3 vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-6-27b.json", "title": "GLM-5.3 vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-6-35b-a3b.json", "title": "GLM-5.3 vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-8-27b.json", "title": "GLM-5.3 vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-8-flash-next.json", "title": "GLM-5.3 vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-coder-30b-a3b-instruct.json", "title": "GLM-5.3 vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-coder-next.json", "title": "GLM-5.3 vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-omni-30b-a3b-instruct.json", "title": "GLM-5.3 vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-2b-instruct.json", "title": "GLM-5.3 vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-30b-a3b-instruct.json", "title": "GLM-5.3 vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-32b-instruct.json", "title": "GLM-5.3 vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-4b-instruct.json", "title": "GLM-5.3 vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-8b-instruct.json", "title": "GLM-5.3 vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwopus3-8-27b-flash-v2.json", "title": "GLM-5.3 vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-recursive-flint.json", "title": "GLM-5.3 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-ripple-65b-preview.json", "title": "GLM-5.3 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-sensenova-loop-9b-preview.json", "title": "GLM-5.3 vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-smollm3-3b.json", "title": "GLM-5.3 vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-spark-x2-6-4b.json", "title": "GLM-5.3 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-step-3-7-flash.json", "title": "GLM-5.3 vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-swift-1-5-qwen3-8-27b.json", "title": "GLM-5.3 vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-swift-1-5-qwen3-8-flash-next.json", "title": "GLM-5.3 vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-thinkingcap-qwen3-8-27b.json", "title": "GLM-5.3 vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-unlimited-ocr-2.json", "title": "GLM-5.3 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-wevisone-vl-2b.json", "title": "GLM-5.3 vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-wevisone-vl-4b.json", "title": "GLM-5.3 vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-zaya1-8b.json", "title": "GLM-5.3 vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-zaya1-8b" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 35, "devstral-small-2": 90, "edge": "devstral-small-2", "glm-5-3": 55, "key": "reach", "name": "Reach", "weight": 25 }, { "by": 10, "devstral-small-2": 60, "edge": "devstral-small-2", "glm-5-3": 50, "key": "risk", "name": "Risk", "weight": 20 }, { "by": 5, "devstral-small-2": 65, "edge": "glm-5-3", "glm-5-3": 70, "key": "interface", "name": "Agent interface", "weight": 10 }, { "by": 12, "devstral-small-2": 46, "edge": "glm-5-3", "glm-5-3": 58, "key": "upkeep", "name": "Documentation and upkeep", "weight": 10 } ], "summary": "GLM-5.3 scores 64.6 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk. Both do open-weight models you run yourself.", "tasks": null, "tutorials": [], "verdicts": { "devstral-small-2": "The easy one to run: a 24B coding agent under Apache 2.0 that five runtimes carry, 15 GB at 4 bits in Ollama, with a 256K context, image input and well-documented tool calling. It's eleven months old, calls tools one at a time, has no reasoning mode, and its card says nothing on limits, safety or data.", "glm-5-3": "A large coding and long-horizon agent model with a 1M-token context, several tool calls per turn and three reasoning budgets. Z.ai's smallest build is 756 GB in FP8, so it needs an 8-GPU server, Z.ai's API or a provider. The main risks are no published safety work, no way to report a flaw, and thinking that can't be turned off." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3", "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3.min.md" }, "markdown": "GLM-5.3 scores 64.6 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk. Both do open-weight models you run yourself.\n\n- Devstral Small 2: grade C, 61/100, rank #60 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/devstral-small-2.md · JSON https://www.anchorterminal.com/api/v1/tools/devstral-small-2.json\n- GLM-5.3: grade B, 64.6/100, rank #21 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/glm-5-3.md · JSON https://www.anchorterminal.com/api/v1/tools/glm-5-3.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 6359 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### Devstral Small 2 (C)\n\nGood for: Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac\n\nAhead on:\n- Reach, 90 against 55\n- Risk, 60 against 50\n\nWatch for: No limitations, safety results, languages or data on the card\n\n### GLM-5.3 (B)\n\nGood for: Teams with an 8-GPU server who want an open coding and long-horizon agent model with a 1M-token context, or agents that call it through Z.ai or a hosted provider\n\nAhead on:\n- Agent interface, 70 against 65\n- Documentation and upkeep, 58 against 46\n\nWatch for: Z.ai's smallest build is 755.6 GB in FP8, with no local Ollama or LM Studio build\n\n\n## Why the edge\n\n### Reach: Devstral Small 2 +35\n\n- Devstral Small 2 (90): Memory 25, the smallest build at 4 bits from a runtime's own library is Ollama's devstral-small-2 at Q4_K_M, 15 GB, and 15 GB × 1.2 = 18 GB, within 24 GB. Mistral's own FP8 files are 25.79 GB. Runtimes 25, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the mistral3 model, llama.cpp b12242 has the architecture with a GGUF from its own organisation, and Ollama's library has devstral-small-2. Builds 10, one quantised precision from Mistral, the FP8 weights it releases. Terms 15, Apache 2.0 in the card's metadata and text, an OSI licence with nothing added. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Mistral's own API serves Devstral Small 2: the card says the model is available through its API and points there when a local runtime underperforms. 25 + 25 + 10 + 15 + 10 + 5 = 90.\n- GLM-5.3 (55): Memory earns nothing, since Z.ai's smallest build is the 755.6 GB FP8 one, about 907 GB with the fifth added, and Ollama only lists a cloud entry. Four runtimes run it in a released version, llama.cpp, vLLM, SGLang and Transformers, for 20, while Ollama and LM Studio have no local build. Z.ai publishes one quantised build, FP8, for 10, since the BF16 repository is the full precision. The GLM-5.3 License is a custom licence that is free for commercial use below a revenue threshold, for 10. The files download with no account or gate, for 10, and Z.ai's own API plus eight live providers on Hugging Face serve it, for 5.\n\n### Documentation and upkeep: GLM-5.3 +12\n\n- Devstral Small 2 (46): Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the last commit, on 15 July 2026, updated the files to match mistral-common, 118 days before this check and within 180. Responsiveness 10, Of the 23 most recent discussions that aren't pull requests (9 December 2025 to 6 November 2026), 11 have a reply from a mistralai member, which is some. Version policy 5, Devstral Small 1.1 stays in its own repository, which this card links as the predecessor, with no dated note on the older card that we read. File health 10, Config, template, tokenizer and card agree, and the June and July commits fixed stray tokens and brought the files in line with mistral-common. 11 + 0 + 10 + 10 + 5 + 10 = 46.\n- GLM-5.3 (58): The card covers intended use, languages and context and misses limitations, architecture, parameters and cut-off, for 8. Training data is 5, a description of the GLM-5 corpus in the cited report with no cut-off. The last change, a chat template speed-up on 14 October in the FP8 repository and on 15 October in the BF16 one, is within 30 days on 2 November, for 20. Responsiveness is 5, as zai-org answered 2 of the 16 discussions that aren't pull requests, the last on 8 September, which is a few, and no discussion has been opened since 10 October. Version policy is the full 10, with each GLM-5 release in its own repository and a dated blog saying what changed from GLM-5.2. File health is the full 10, with files and card agreeing and no broken-file report waiting by title.\n\n### Risk: Devstral Small 2 +10\n\n- Devstral Small 2 (60): File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, files in Mistral's verified mistralai organisation, which Mistral's site links to per our Mistral Large 4 listing (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 5, mistral.ai's security.txt gives a security contact and a submission policy, as read for the Mistral Large 4 listing (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.\n- GLM-5.3 (50): File safety is full, with safetensors only, no Python in the repository and no remote code needed in Transformers 5.12.0 or later. Provenance is full, files in the zai-org organisation Z.ai links to with a SHA-256 for every shard. Safety evaluation is 0, because the blog mentions safety evaluation and hardening but publishes no results, and agent guidance is 0, with nothing on refusals, prompt injection or cautions. Licence risk is 10, losing 5 for the security review that model-as-a-service operators above US$10 billion of revenue must pass. The security programme is 0, with no security.txt, no SECURITY.md and no advisories.\n\n### Agent interface: GLM-5.3 +5\n\n- Devstral Small 2 (65): Chat template 20, chat_template.jinja in the repository (11,362 characters), with the tokenizer's tekken file for mistral-common. Tool-calling format 25, the card documents tools in the OpenAI function format with an example, names the mistral tool-call parser with auto tool choice for vLLM, shows the same for SGLang, and ships test prompts with the expected tool-call output. Trained tool calling 10, the card says the model excels at using tools, and its tests cover one tool call and calls made one at a time in sequence. Structured output 0, Nothing on the card about JSON or schema-constrained answers for this model. Reasoning control 0, no reasoning mode is documented, and a June 2026 commit removed stray thinking tokens from the files. Context 10, 256K tokens per the card, served at 262,144 in its vLLM command. 20 + 25 + 10 + 0 + 0 + 10 = 65.\n- GLM-5.3 (70): A Jinja chat template sits in the repository, for 20. The tool-calling format is 10, since it is defined only by the template and the glm47 parser is named by vLLM and SGLang rather than by Z.ai. The template takes several calls in one turn, for 20. Structured output is 0, with nothing on the card and JSON documented only for the hosted API. Reasoning control is 10, a per-request budget through reasoning_effort with the reasoning in a think block, though thinking can't be turned off. Context is 10, 1,048,576 tokens native with no rope scaling.\n\n## Score by category\n\n| Category | Weight | Devstral Small 2 | GLM-5.3 | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 90 | 55 | Devstral Small 2 +35 |\n| Risk | 20% (20 this run) | 60 | 50 | Devstral Small 2 +10 |\n| Agent interface | 10% (10 this run) | 65 | 70 | GLM-5.3 +5 |\n| Documentation and upkeep | 10% (10 this run) | 46 | 58 | GLM-5.3 +12 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **61 · C** | **64.6 · B** | |\n\n## Facts side by side\n\n| Fact | Devstral Small 2 | GLM-5.3 |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Mistral AI | Z.ai (Zhipu AI) |\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 | GLM-5.3 License (MIT-style, with a security review for the largest model-as-a-service operators) |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-07-15 | 2026-10-15 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | none | 2.8/5 (4) |\n\n## Verdicts\n\n**Devstral Small 2.** The easy one to run: a 24B coding agent under Apache 2.0 that five runtimes carry, 15 GB at 4 bits in Ollama, with a 256K context, image input and well-documented tool calling. It's eleven months old, calls tools one at a time, has no reasoning mode, and its card says nothing on limits, safety or data.\n\n**GLM-5.3.** A large coding and long-horizon agent model with a 1M-token context, several tool calls per turn and three reasoning budgets. Z.ai's smallest build is 756 GB in FP8, so it needs an 8-GPU server, Z.ai's API or a provider. The main risks are no published safety work, no way to report a flaw, and thinking that can't be turned off.\n\n## Before you call either\n\n### Devstral Small 2\n\n1. `ollama run devstral-small-2` is the quickest start, at 15 GB\n2. On vLLM pass `--tool-call-parser mistral --enable-auto-tool-choice`\n3. Send the system prompt from CHAT_SYSTEM_PROMPT.txt in the repository. The card says results depend on it\n4. Use a low temperature. The repository's default is 0.15\n5. Plan for one tool call per turn\n6. The same model is on our Mistral API listing if you'd rather not host it\n\n### GLM-5.3\n\n1. Start it with `vllm serve zai-org/GLM-5.3 --kv-cache-dtype fp8 --tensor-parallel-size 8 --speculative-config.method mtp --speculative-config.num_speculative_tokens 5 --tool-call-parser glm47 --reasoning-parser glm47 --enable-auto-tool-choice --served-model-name glm-5.3` (vLLM 0.28.0 or later, 8xH200 or 8xH20 per vLLM's recipe)\n2. Use the glm47 tool-call and reasoning parsers in vLLM or SGLang; SGLang's cookbook says glm45 leaves the calls as plain text\n3. Pass `chat_template_kwargs: {\"reasoning_effort\": \"low\"}` for short tasks; anything other than low or high falls back to max\n4. Pass `clear_thinking: true` in chat use, since the template keeps earlier reasoning by default\n5. Don't send `enable_thinking: false`; the template ignores it and always opens a think block\n6. Validate JSON output yourself, since structured output is documented only for Z.ai's hosted API\n7. No Z.ai build fits a 128 GB machine; the full 1M context needs 8xB200 per vLLM's recipe\n\n## Questions\n\n### Which is better for AI agents, Devstral Small 2 or GLM-5.3?\n\nGLM-5.3 scores 64.6 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3.json, and with the fewest tokens: https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"devstral-small-2\", \"b\": \"glm-5-3\"}`. From a terminal: `anchor compare devstral-small-2 glm-5-3`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/devstral-small-2.json and https://www.anchorterminal.com/api/v1/tools/glm-5-3.json\n\n## Other comparisons with Devstral Small 2 or GLM-5.3\n\n- [Agents-A1-4B vs Devstral Small 2](https://www.anchorterminal.com/compare/agents-a1-4b-vs-devstral-small-2.md)\n- [Agents-A1-4B vs GLM-5.3](https://www.anchorterminal.com/compare/agents-a1-4b-vs-glm-5-3.md)\n- [Apertus v1.5 8B vs Devstral Small 2](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-devstral-small-2.md)\n- [Apertus v1.5 8B vs GLM-5.3](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-glm-5-3.md)\n- [Apodex-1.1-mini vs Devstral Small 2](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-devstral-small-2.md)\n- [Apodex-1.1-mini vs GLM-5.3](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-glm-5-3.md)\n- [Arete-27B vs Devstral Small 2](https://www.anchorterminal.com/compare/arete-27b-vs-devstral-small-2.md)\n- [Arete-27B vs GLM-5.3](https://www.anchorterminal.com/compare/arete-27b-vs-glm-5-3.md)\n- [BigBang-v1 vs Devstral Small 2](https://www.anchorterminal.com/compare/bigbang-v1-vs-devstral-small-2.md)\n- [BigBang-v1 vs GLM-5.3](https://www.anchorterminal.com/compare/bigbang-v1-vs-glm-5-3.md)\n- [Carbon-X vs Devstral Small 2](https://www.anchorterminal.com/compare/carbon-x-vs-devstral-small-2.md)\n- [Carbon-X vs GLM-5.3](https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3.md)\n- [Cola2 vs Devstral Small 2](https://www.anchorterminal.com/compare/cola2-vs-devstral-small-2.md)\n- [Cola2 vs GLM-5.3](https://www.anchorterminal.com/compare/cola2-vs-glm-5-3.md)\n- [Cosmos-Reason2-2B vs Devstral Small 2](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-devstral-small-2.md)\n- [Cosmos-Reason2-2B vs GLM-5.3](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-glm-5-3.md)\n- [Darwin-36B-Opus vs Devstral Small 2](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-devstral-small-2.md)\n- [Darwin-36B-Opus vs GLM-5.3](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-glm-5-3.md)\n- [DeepSeek-V3.2 vs Devstral Small 2](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-devstral-small-2.md)\n- [DeepSeek-V3.2 vs GLM-5.3](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-5-3.md)\n- [DeepSeek V4.1 Flash vs Devstral Small 2](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-devstral-small-2.md)\n- [DeepSeek V4.1 Flash vs GLM-5.3](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-glm-5-3.md)\n- [DeepSeek-V4-Flash-0731 vs Devstral Small 2](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-devstral-small-2.md)\n- [DeepSeek-V4-Flash-0731 vs GLM-5.3](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-glm-5-3.md)\n- [Devstral Small 2 vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-diffusiongemma-26b-a4b-it.md)\n- [Devstral Small 2 vs EXAONE 4.5 33B](https://www.anchorterminal.com/compare/devstral-small-2-vs-exaone-4-5-33b.md)\n- [Devstral Small 2 vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-12b-it.md)\n- [Devstral Small 2 vs Gemma 4 26B A4B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-26b-a4b-it.md)\n- [Devstral Small 2 vs Gemma 4 31B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-31b-it.md)\n- [Devstral Small 2 vs Gemma 4 E2B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e2b-it.md)\n- [Devstral Small 2 vs Gemma 4 E4B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e4b-it.md)\n- [Devstral Small 2 vs GLM-4.5-Air](https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-5-air.md)\n- [Devstral Small 2 vs GLM-4.7-Flash](https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-7-flash.md)\n- [Devstral Small 2 vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash.md)\n- [Devstral Small 2 vs gpt-oss-120b](https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-120b.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 Granite 4.2 30B](https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-30b.md)\n- [Devstral Small 2 vs Granite 4.2 3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-3b.md)\n- [Devstral Small 2 vs Granite 4.2 8B](https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-8b.md)\n- [Devstral Small 2 vs Hy-Memory-30B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-hy-memory-30b-a3b.md)\n- [Devstral Small 2 vs Hy3](https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3.md)\n- [Devstral Small 2 vs Inkling](https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling.md)\n- [Devstral Small 2 vs Inkling-Small](https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-small.md)\n- [Devstral Small 2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/devstral-small-2-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [Devstral Small 2 vs Kimi K3](https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3.md)\n- [Devstral Small 2 vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3-1-pro.md)\n- [Devstral Small 2 vs Kolibri-1](https://www.anchorterminal.com/compare/devstral-small-2-vs-kolibri-1.md)\n- [Devstral Small 2 vs Kronos](https://www.anchorterminal.com/compare/devstral-small-2-vs-kronos.md)\n- [Devstral Small 2 vs Laguna M.1](https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-m-1.md)\n- [Devstral Small 2 vs Laguna S 2.1](https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-s-2-1.md)\n- [Devstral Small 2 vs Laguna XS 2.1](https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-xs-2-1.md)\n- [Devstral Small 2 vs LBS-27B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lbs-27b.md)\n- [Devstral Small 2 vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm2-5-2-6b.md)\n- [Devstral Small 2 vs LFM3-1.7B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-1-7b.md)\n- [Devstral Small 2 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-audio-2b.md)\n- [Devstral Small 2 vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-omni-2b.md)\n- [Devstral Small 2 vs LFM3-VL-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-vl-2b.md)\n- [Devstral Small 2 vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-0-tiny.md)\n- [Devstral Small 2 vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-1-flash-1019.md)\n- [Devstral Small 2 vs LongCat-2.5](https://www.anchorterminal.com/compare/devstral-small-2-vs-longcat-2-5.md)\n- [Devstral Small 2 vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Devstral Small 2 vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-flash-rl.md)\n- [Devstral Small 2 vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-o-4-5.md)\n- [Devstral Small 2 vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-1b.md)\n- [Devstral Small 2 vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-35b-a3b.md)\n- [Devstral Small 2 vs MiniCPM5-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm5-2b.md)\n- [Devstral Small 2 vs MiniMax-M2.5](https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-5.md)\n- [Devstral Small 2 vs MiniMax-M2.7](https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-7.md)\n- [Devstral Small 2 vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m3-1-flash.md)\n- [Devstral Small 2 vs Mistral Large 4](https://www.anchorterminal.com/compare/devstral-small-2-vs-mistral-large-4.md)\n- [Devstral Small 2 vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/devstral-small-2-vs-muse-glimmer-30b.md)\n- [Devstral Small 2 vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-2-3b.md)\n- [Devstral Small 2 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-3-33b.md)\n- [Devstral Small 2 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Devstral Small 2 vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Devstral Small 2 vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-30b-a3b.md)\n- [Devstral Small 2 vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-4b.md)\n- [Devstral Small 2 vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Devstral Small 2 vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-super-120b-a12b.md)\n- [Devstral Small 2 vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-ultra-550b-a55b.md)\n- [Devstral Small 2 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/devstral-small-2-vs-north-mini-code-1-0.md)\n- [Devstral Small 2 vs occamy-1.0](https://www.anchorterminal.com/compare/devstral-small-2-vs-occamy-1-0.md)\n- [Devstral Small 2 vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/devstral-small-2-vs-olmo-3-7b-think.md)\n- [Devstral Small 2 vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-122b.md)\n- [Devstral Small 2 vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-35b-a3b.md)\n- [Devstral Small 2 vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-397b.md)\n- [Devstral Small 2 vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-9b.md)\n- [Devstral Small 2 vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-otel-2-0-llm-31b-it.md)\n- [Devstral Small 2 vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen-agentworld-35b-a3b.md)\n- [Devstral Small 2 vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Devstral Small 2 vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-4b-instruct-2507.md)\n- [Devstral Small 2 vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-0-8b.md)\n- [Devstral Small 2 vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-122b-a10b.md)\n- [Devstral Small 2 vs Qwen3.5-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-2b.md)\n- [Devstral Small 2 vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-397b-a17b.md)\n- [Devstral Small 2 vs Qwen3.5-4B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-4b.md)\n- [Devstral Small 2 vs Qwen3.5-9B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-9b.md)\n- [Devstral Small 2 vs Qwen3.6-27B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-27b.md)\n- [Devstral Small 2 vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-35b-a3b.md)\n- [Devstral Small 2 vs Qwen3.8-27B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-27b.md)\n- [Devstral Small 2 vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-flash-next.md)\n- [Devstral Small 2 vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Devstral Small 2 vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-next.md)\n- [Devstral Small 2 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-2b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-32b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-4b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-8b-instruct.md)\n- [Devstral Small 2 vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwopus3-8-27b-flash-v2.md)\n- [Devstral Small 2 vs Recursive Flint](https://www.anchorterminal.com/compare/devstral-small-2-vs-recursive-flint.md)\n- [Devstral Small 2 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/devstral-small-2-vs-ripple-65b-preview.md)\n- [Devstral Small 2 vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/devstral-small-2-vs-sensenova-loop-9b-preview.md)\n- [Devstral Small 2 vs SmolLM3-3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-smollm3-3b.md)\n- [Devstral Small 2 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/devstral-small-2-vs-spark-x2-6-4b.md)\n- [Devstral Small 2 vs Step 3.7 Flash](https://www.anchorterminal.com/compare/devstral-small-2-vs-step-3-7-flash.md)\n- [Devstral Small 2 vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-27b.md)\n- [Devstral Small 2 vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Devstral Small 2 vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/devstral-small-2-vs-thinkingcap-qwen3-8-27b.md)\n- [Devstral Small 2 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/devstral-small-2-vs-unlimited-ocr-2.md)\n- [Devstral Small 2 vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-2b.md)\n- [Devstral Small 2 vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-4b.md)\n- [Devstral Small 2 vs ZAYA1-8B](https://www.anchorterminal.com/compare/devstral-small-2-vs-zaya1-8b.md)\n- [DiffusionGemma 26B A4B IT vs GLM-5.3](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3.md)\n- [EXAONE 4.5 33B vs GLM-5.3](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-glm-5-3.md)\n- [Gemma 4 12B IT vs GLM-5.3](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3.md)\n- [Gemma 4 26B A4B IT vs GLM-5.3](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-glm-5-3.md)\n- [Gemma 4 31B IT vs GLM-5.3](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-glm-5-3.md)\n- [Gemma 4 E2B IT vs GLM-5.3](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-glm-5-3.md)\n- [Gemma 4 E4B IT vs GLM-5.3](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-glm-5-3.md)\n- [GLM-4.5-Air vs GLM-5.3](https://www.anchorterminal.com/compare/glm-4-5-air-vs-glm-5-3.md)\n- [GLM-4.7-Flash vs GLM-5.3](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-glm-5-3.md)\n- [GLM-5.3 vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/glm-5-3-vs-glm-5-3-flash.md)\n- [GLM-5.3 vs gpt-oss-120b](https://www.anchorterminal.com/compare/glm-5-3-vs-gpt-oss-120b.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 Granite 4.2 30B](https://www.anchorterminal.com/compare/glm-5-3-vs-granite-4-2-30b.md)\n- [GLM-5.3 vs Granite 4.2 3B](https://www.anchorterminal.com/compare/glm-5-3-vs-granite-4-2-3b.md)\n- [GLM-5.3 vs Granite 4.2 8B](https://www.anchorterminal.com/compare/glm-5-3-vs-granite-4-2-8b.md)\n- [GLM-5.3 vs Hy-Memory-30B-A3B](https://www.anchorterminal.com/compare/glm-5-3-vs-hy-memory-30b-a3b.md)\n- [GLM-5.3 vs Hy3](https://www.anchorterminal.com/compare/glm-5-3-vs-hy3.md)\n- [GLM-5.3 vs Inkling](https://www.anchorterminal.com/compare/glm-5-3-vs-inkling.md)\n- [GLM-5.3 vs Inkling-Small](https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-small.md)\n- [GLM-5.3 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/glm-5-3-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [GLM-5.3 vs Kimi K3](https://www.anchorterminal.com/compare/glm-5-3-vs-kimi-k3.md)\n- [GLM-5.3 vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/glm-5-3-vs-kimi-k3-1-pro.md)\n- [GLM-5.3 vs Kolibri-1](https://www.anchorterminal.com/compare/glm-5-3-vs-kolibri-1.md)\n- [GLM-5.3 vs Kronos](https://www.anchorterminal.com/compare/glm-5-3-vs-kronos.md)\n- [GLM-5.3 vs Laguna M.1](https://www.anchorterminal.com/compare/glm-5-3-vs-laguna-m-1.md)\n- [GLM-5.3 vs Laguna S 2.1](https://www.anchorterminal.com/compare/glm-5-3-vs-laguna-s-2-1.md)\n- [GLM-5.3 vs Laguna XS 2.1](https://www.anchorterminal.com/compare/glm-5-3-vs-laguna-xs-2-1.md)\n- [GLM-5.3 vs LBS-27B](https://www.anchorterminal.com/compare/glm-5-3-vs-lbs-27b.md)\n- [GLM-5.3 vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/glm-5-3-vs-lfm2-5-2-6b.md)\n- [GLM-5.3 vs LFM3-1.7B](https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-1-7b.md)\n- [GLM-5.3 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-audio-2b.md)\n- [GLM-5.3 vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-omni-2b.md)\n- [GLM-5.3 vs LFM3-VL-2B](https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-vl-2b.md)\n- [GLM-5.3 vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/glm-5-3-vs-ling-3-0-tiny.md)\n- [GLM-5.3 vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/glm-5-3-vs-ling-3-1-flash-1019.md)\n- [GLM-5.3 vs LongCat-2.5](https://www.anchorterminal.com/compare/glm-5-3-vs-longcat-2-5.md)\n- [GLM-5.3 vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/glm-5-3-vs-mimo-v2-6-distill-qwen-9b.md)\n- [GLM-5.3 vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/glm-5-3-vs-mimo-v2-6-flash-rl.md)\n- [GLM-5.3 vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm-o-4-5.md)\n- [GLM-5.3 vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm-v-4-7-1b.md)\n- [GLM-5.3 vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm-v-4-7-35b-a3b.md)\n- [GLM-5.3 vs MiniCPM5-2B](https://www.anchorterminal.com/compare/glm-5-3-vs-minicpm5-2b.md)\n- [GLM-5.3 vs MiniMax-M2.5](https://www.anchorterminal.com/compare/glm-5-3-vs-minimax-m2-5.md)\n- [GLM-5.3 vs MiniMax-M2.7](https://www.anchorterminal.com/compare/glm-5-3-vs-minimax-m2-7.md)\n- [GLM-5.3 vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/glm-5-3-vs-minimax-m3-1-flash.md)\n- [GLM-5.3 vs Mistral Large 4](https://www.anchorterminal.com/compare/glm-5-3-vs-mistral-large-4.md)\n- [GLM-5.3 vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/glm-5-3-vs-muse-glimmer-30b.md)\n- [GLM-5.3 vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/glm-5-3-vs-nanbeige-4-2-3b.md)\n- [GLM-5.3 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/glm-5-3-vs-nanbeige-4-3-33b.md)\n- [GLM-5.3 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [GLM-5.3 vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [GLM-5.3 vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-nano-30b-a3b.md)\n- [GLM-5.3 vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-nano-4b.md)\n- [GLM-5.3 vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [GLM-5.3 vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-super-120b-a12b.md)\n- [GLM-5.3 vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/glm-5-3-vs-nemotron-3-ultra-550b-a55b.md)\n- [GLM-5.3 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/glm-5-3-vs-north-mini-code-1-0.md)\n- [GLM-5.3 vs occamy-1.0](https://www.anchorterminal.com/compare/glm-5-3-vs-occamy-1-0.md)\n- [GLM-5.3 vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/glm-5-3-vs-olmo-3-7b-think.md)\n- [GLM-5.3 vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-122b.md)\n- [GLM-5.3 vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-35b-a3b.md)\n- [GLM-5.3 vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-397b.md)\n- [GLM-5.3 vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/glm-5-3-vs-ornith-1-5-9b.md)\n- [GLM-5.3 vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/glm-5-3-vs-otel-2-0-llm-31b-it.md)\n- [GLM-5.3 vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen-agentworld-35b-a3b.md)\n- [GLM-5.3 vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-30b-a3b-instruct-2507.md)\n- [GLM-5.3 vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-4b-instruct-2507.md)\n- [GLM-5.3 vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-0-8b.md)\n- [GLM-5.3 vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-122b-a10b.md)\n- [GLM-5.3 vs Qwen3.5-2B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-2b.md)\n- [GLM-5.3 vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-397b-a17b.md)\n- [GLM-5.3 vs Qwen3.5-4B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-4b.md)\n- [GLM-5.3 vs Qwen3.5-9B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-5-9b.md)\n- [GLM-5.3 vs Qwen3.6-27B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-6-27b.md)\n- [GLM-5.3 vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-6-35b-a3b.md)\n- [GLM-5.3 vs Qwen3.8-27B](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-8-27b.md)\n- [GLM-5.3 vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-8-flash-next.md)\n- [GLM-5.3 vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-coder-30b-a3b-instruct.md)\n- [GLM-5.3 vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-coder-next.md)\n- [GLM-5.3 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-omni-30b-a3b-instruct.md)\n- [GLM-5.3 vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-2b-instruct.md)\n- [GLM-5.3 vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-30b-a3b-instruct.md)\n- [GLM-5.3 vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-32b-instruct.md)\n- [GLM-5.3 vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-4b-instruct.md)\n- [GLM-5.3 vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-vs-qwen3-vl-8b-instruct.md)\n- [GLM-5.3 vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/glm-5-3-vs-qwopus3-8-27b-flash-v2.md)\n- [GLM-5.3 vs Recursive Flint](https://www.anchorterminal.com/compare/glm-5-3-vs-recursive-flint.md)\n- [GLM-5.3 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-5-3-vs-ripple-65b-preview.md)\n- [GLM-5.3 vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/glm-5-3-vs-sensenova-loop-9b-preview.md)\n- [GLM-5.3 vs SmolLM3-3B](https://www.anchorterminal.com/compare/glm-5-3-vs-smollm3-3b.md)\n- [GLM-5.3 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/glm-5-3-vs-spark-x2-6-4b.md)\n- [GLM-5.3 vs Step 3.7 Flash](https://www.anchorterminal.com/compare/glm-5-3-vs-step-3-7-flash.md)\n- [GLM-5.3 vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/glm-5-3-vs-swift-1-5-qwen3-8-27b.md)\n- [GLM-5.3 vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/glm-5-3-vs-swift-1-5-qwen3-8-flash-next.md)\n- [GLM-5.3 vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/glm-5-3-vs-thinkingcap-qwen3-8-27b.md)\n- [GLM-5.3 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/glm-5-3-vs-unlimited-ocr-2.md)\n- [GLM-5.3 vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/glm-5-3-vs-wevisone-vl-2b.md)\n- [GLM-5.3 vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/glm-5-3-vs-wevisone-vl-4b.md)\n- [GLM-5.3 vs ZAYA1-8B](https://www.anchorterminal.com/compare/glm-5-3-vs-zaya1-8b.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": "2026-11-11", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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": "Devstral Small 2 vs GLM-5.3", "url": "" } ], "description": "GLM-5.3 scores 64.6 (B) to Devstral Small 2's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Devstral Small 2 C 61", "GLM-5.3 B 64.6", "scores" ], "h1": "Devstral Small 2 vs GLM-5.3", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/devstral-small-2-vs-glm-5-3", "published": "2026-10-01", "section": "tools", "title": "Devstral Small 2 vs GLM-5.3 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3" }, "tokens": { "markdown": 9350, "slim": 830 }, "version": 1 }