{ "data": { "a": { "slug": "deepseek-v3-2", "name": "DeepSeek-V3.2", "vendor": "DeepSeek", "vendorUrl": "https://www.deepseek.com", "kind": "weights", "category": "open-weights", "summary": "DeepSeek-V3.2 is DeepSeek's open-weight mixture-of-experts reasoning model with DeepSeek Sparse Attention, trained for tool use with a 128K-token context, published in FP8 under MIT. DeepSeek's API stopped serving it on 24 April 2026, moving to V4 Flash.", "url": "https://www.anchorterminal.com/tools/deepseek-v3-2", "markdownUrl": "https://www.anchorterminal.com/tools/deepseek-v3-2.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/deepseek-v3-2.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/deepseek-v3-2.json", "repo": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "license": "MIT", "transports": [], "packages": [ { "registry": "huggingface", "name": "deepseek-ai/DeepSeek-V3.2" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-10-21).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under the MIT licence. DeepSeek's own API served V3.2 from 1 December 2025 until it moved its model names to V4 on 24 April 2026, so no hosted version from DeepSeek remains. Running it yourself costs the hardware, 689.5 GB of 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": "2026-10-21" }, "docsUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "reasoning", "tool-calling", "mit", "safetensors", "fp8", "self-hosted" ], "lastRelease": "2025-12-01", "graded": true, "anchor": { "graded": true, "score": 58.6, "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": 1201, "categoryRank": 56, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 69, "interface": 60, "reach": 60, "risk": 50, "upkeep": 34 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-21" }, "negative": 0, "verdict": "DeepSeek-V3.2 is an MIT-licensed reasoning model trained for parallel tool calls, with thinking chosen per request, for long agent work. It needs about 690 GB of FP8 files, eight 80 GB GPUs in vLLM's recipe and prompts built from DeepSeek's Python. The main risk is neglect, with no file changes since December 2025 and no safety evaluation.", "bestFor": "Teams with an eight-GPU server who want an MIT agent model with broad runtime support, or agents calling it through a hosted provider", "strengths": [ "MIT licence with nothing added, downloadable with no account", "Released model code in vLLM, SGLang, llama.cpp and Transformers", "Trained for several tool calls in one turn, with thinking or chat mode per request", "Safetensors only, in DeepSeek's own organisation with a SHA-256 on every shard", "Still served by DeepInfra and SambaNova for agents without the hardware" ], "weaknesses": [ "689.5 GB of FP8 files and no smaller build from DeepSeek or a runtime library, far beyond 107.4 GB", "No Jinja template, so prompts come from running DeepSeek's encoding code", "DeepSeek names no runtime tool parser and documents no structured output", "No change since 1 December 2025 and no DeepSeek reply in its discussions", "No safety evaluation, agent-use guidance, languages or knowledge cut-off published" ], "agentNotes": [ "Start it with vLLM's recipe, vllm serve deepseek-ai/DeepSeek-V3.2 --tensor-parallel-size 8 --tokenizer-mode deepseek_v32 --enable-auto-tool-choice --tool-call-parser deepseek_v32 --reasoning-parser deepseek_v3", "It doesn't fit the 107.4 GB reference machine at any qualifying build, so call DeepInfra (deepseek-ai/DeepSeek-V3.2) or SambaNova (DeepSeek-V3.2) instead", "Outside vLLM, build prompts with encoding/encoding_dsv32.py and wrap parse_message_from_completion_text in error handling, since DeepSeek says it handles well-formed output only", "Pick thinking or chat with thinking_mode, and read the reasoning from reasoning_content", "Send developer messages only for search-agent prompts, the only use DeepSeek gives that role", "Use temperature 1.0 and top_p 0.95 and keep prompts within 128K tokens" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.3, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 58.6 } ], "editorialScores": { "capability": 69, "interface": 60, "reach": 60, "risk": 50, "upkeep": 34 }, "provenanceScore": 60, "checked": { "categories": { "capability": "2026-10-21", "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# vLLM's own recipe for DeepSeek-V3.2 (8 GPUs)\nvllm serve deepseek-ai/DeepSeek-V3.2 --tensor-parallel-size 8 \\\n --tokenizer-mode deepseek_v32 --enable-auto-tool-choice \\\n --tool-call-parser deepseek_v32 --reasoning-parser deepseek_v3\n# or DeepSeek's reference demo, from the inference folder\npython convert.py --hf-ckpt-path \"$HF_CKPT_PATH\" --save-path \"$SAVE_PATH\" --n-experts 256 --model-parallel 8\ntorchrun --nproc-per-node 8 generate.py --ckpt-path \"$SAVE_PATH\" --config config_671B_v3.2.json --interactive" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/deepseek-v3-2" }, "sameCompany": [ "deepseek-api", "deepseek-search-api", "deepseek-v4-1-flash", "deepseek-v4-flash-0731" ], "weights": { "trainedBy": "DeepSeek", "builtOn": "deepseek-ai/DeepSeek-V3.2-Exp-Base (continued from DeepSeek-V3.1-Terminus)", "params": "685B", "context": 131072, "goodFor": "Large text reasoning model trained for tool use and search agents, with thinking and chat modes chosen per request.", "runtimes": [ "llama.cpp", "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "DeepSeek-V3.2", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "who": "publisher", "precision": "fp8", "sizeGB": 689.5, "memoryGB": 1024, "format": "safetensors", "note": "Native FP8 (E4M3) with BF16 and F32 for the rest; the only build DeepSeek publishes" } ], "run": "vllm serve deepseek-ai/DeepSeek-V3.2 --tensor-parallel-size 8 --tokenizer-mode deepseek_v32 --enable-auto-tool-choice --tool-call-parser deepseek_v32 --reasoning-parser deepseek_v3", "runBuild": "DeepSeek-V3.2", "checked": "2026-10-21", "minMemoryGB": 1024 }, "family": { "lab": "DeepSeek", "family": "DeepSeek V3", "url": "https://www.anchorterminal.com/open-weights/#deepseek", "others": [ { "name": "DeepSeek-V3-Base", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3-Base", "params": "671B total, 37B activated" }, { "name": "DeepSeek-V3", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "params": "671B total, 37B activated" }, { "name": "DeepSeek-V3-0324", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3-0324", "params": "not stated on card" }, { "name": "DeepSeek-V3.1-Base", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base", "params": "671B total, 37B activated" }, { "name": "DeepSeek-V3.1", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "params": "671B total, 37B activated" }, { "name": "DeepSeek-V3.1-Terminus", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus", "params": "not stated on card" }, { "name": "DeepSeek-V3.2-Exp-Base", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp-Base", "params": "not stated on card" }, { "name": "DeepSeek-V3.2-Exp", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "params": "not stated on card (inference config named config_671B_v3.2.json)" }, { "name": "DeepSeek-V3.2-Speciale", "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale", "params": "not stated on card" } ], "olderCount": 72 }, "area": "models", "provenance": { "legalEntity": "DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)", "domain": "deepseek.com", "domainRegistered": "2000-08-13", "domainNote": "deepseek.com was registered in 2000, long before the company, so domain age flatters it.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The legal entity is the one DeepSeek's platform terms name, read for the deepseek-api listing. The weights' licence names only DeepSeek.", "Nothing is hosted, so the MIT licence stands in for terms of service and no privacy policy is scored.", "No changelog for the weights. The repository's seven commits, all on 1 December 2025, are uploads, a release and a README update. The DeepSeek-V3.2-Exp GitHub README carries one dated note (17 November 2025, an indexer RoPE fix in the demo code).", "RDAP gives 13 August 2000 as the registration date of deepseek.com (read 21 October 2026).", "deepseek.com/.well-known/security.txt and www.deepseek.com/.well-known/security.txt answered 404 on 21 October 2026.", "DeepSeek's site footer has a Report Security Issue link to security@deepseek.com, a company-wide address, read from https://www.deepseek.com/en/transparency/ on 21 October 2026." ], "score": 60 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/deepseek-v3-2.json", "live": { "slug": "deepseek-v3-2", "securityTxt": { "url": "https://deepseek.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-23T15:24:08.745976625Z" }, "updatedAt": "2026-10-23T15:24:08.745976625Z" } }, "answer": "Recursive Flint scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in every scored category.", "b": { "slug": "recursive-flint", "name": "Recursive Flint", "vendor": "Recursive", "vendorUrl": "https://www.recursive.com", "kind": "weights", "category": "open-weights", "summary": "Recursive Flint is Recursive's open-weight mixture-of-experts coding model for agents, 39.8B total and about 2.5B active parameters, with reasoning, tool calling and a 262,144-token context, published on Hugging Face under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/recursive-flint", "markdownUrl": "https://www.anchorterminal.com/tools/recursive-flint.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/recursive-flint.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/recursive-flint.json", "repo": "https://huggingface.co/RecursiveSI/flint", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "RecursiveSI/flint" }, { "registry": "huggingface", "name": "RecursiveSI/flint-int4" }, { "registry": "huggingface", "name": "RecursiveSI/flint-int4-gguf" }, { "registry": "huggingface", "name": "RecursiveSI/flint-nvfp4-gguf" }, { "registry": "ollama", "name": "flint" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The Hub reports gated false for the main repository and all three quantised builds (checked 2026-10-22).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Running it yourself costs the hardware, 79.6 GB for the BF16 files and 22.6 GB for Recursive's smallest 4-bit build (MLX INT4). The card mentions hosted API terms separate from the weight licence, but no Recursive API or inference provider serving Flint was confirmed (checked 2026-10-22).", "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 2026-10-22).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-22" }, "docsUrl": "https://huggingface.co/RecursiveSI/flint", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "coding", "reasoning", "tool-calling", "apache-2.0", "safetensors", "gguf", "mlx", "nvfp4", "self-hosted" ], "lastRelease": "2026-10-21", "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": 1201, "categoryRank": 41, "methodology": "0.6", "run": "2026-10-01", "scores": { "interface": 90, "reach": 75, "risk": 60, "upkeep": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-22" }, "negative": 0, "verdict": "A small-active coding cousin for agents with 32 to 48 GB, built for codebase work with parallel tool calls and JSON output. It needs llama.cpp b11803 or Ollama 0.40.8 or later, and the BF16 checkpoint needs a 141 GB GPU. Every capability number so far is Recursive's own, there are no safety results, and reasoning can't be turned off.", "bestFor": "Agents doing repository work on a 32 to 48 GB Mac or NVIDIA box that want a fast sparse coder with documented tool calls and a plain licence.", "strengths": [ "Plain Apache 2.0 with no gate, account or use policy", "Recursive's own MLX INT4, Q4_1 GGUF and NVFP4 GGUF builds, the smallest 22.6 GB", "Tool format, parser, parallel calls and JSON Schema output documented by Recursive", "262,144 tokens of context with no position scaling", "Safetensors and GGUF only, with a checksum on every file in Recursive's organisation", "llama.cpp, Ollama and LM Studio support on release day" ], "weaknesses": [ "No independent benchmark results yet, every published score is Recursive's", "No reasoning switch or budget, so hard prompts can spend tens of thousands of tokens thinking", "The BF16 route needs one 141 GB GPU and Recursive's SGLang plugin, and vLLM and released Transformers don't run it", "No safety results and no trained instruction hierarchy", "No inference provider or confirmed Recursive API for agents without the hardware" ], "agentNotes": [ "Quickest start is `ollama run flint` (Ollama 0.40.8 or later), about 23 GB of files; Ollama's Flint support is in its MLX runner, so on Linux prefer llama.cpp", "With llama.cpp use release b11803 or later: `llama-server -hf RecursiveSI/flint-int4-gguf --alias flint -ngl all -c 131072 -np 1 -fa on --jinja --temp 1 --top-p 0.95 --top-k 20 --min-p 0`, and keep --jinja on", "Set max_tokens to at least 32768 for hard tasks, reasoning counts against it and can't be switched off, and finish_reason length can mean no answer or tool call came out", "Send reasoning_content back on assistant messages when replaying the conversation, as Recursive's cards ask", "Strip \u003ctool_call\u003e, \u003ctool_response\u003e, \u003carg_key\u003e and \u003carg_value\u003e from untrusted tool output, the template doesn't escape them and a copied \u003c/tool_call\u003e can add a call", "Message content must be a string, flatten content-part arrays first", "Recursive's SGLang servers listen on 0.0.0.0 with no key, publish the port on localhost only or pass --api-key" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 90, "reach": 75, "risk": 60, "upkeep": 67 }, "provenanceScore": 40, "checked": { "categories": { "interface": "2026-10-22", "reach": "2026-10-22", "risk": "2026-10-22", "upkeep": "2026-10-22" }, "last": "2026-10-22", "oldest": "2026-10-22", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "ollama run flint\n# or, with llama.cpp b11803 or later:\nllama-server -hf RecursiveSI/flint-int4-gguf --alias flint -ngl all -c 262144 -np 1 -fa on --jinja \\\n --temp 1 --top-p 0.95 --top-k 20 --min-p 0 --port 8080", "http": "curl http://localhost:11434/api/chat \\\n -d '{\"model\": \"flint\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}]}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/recursive-flint" }, "weights": { "trainedBy": "Recursive", "params": "39.8B total, about 2.5B active", "context": 262144, "goodFor": "Agentic coding on a 32 to 48 GB machine, investigating codebases, fixing bugs and writing tests with multi-turn tool calls and reasoning.", "runtimes": [ "llama.cpp", "Ollama", "LM Studio" ], "builds": [ { "name": "flint-int4", "url": "https://huggingface.co/RecursiveSI/flint-int4", "who": "publisher", "precision": "int4 (group-64 affine, INT8 embeddings)", "sizeGB": 22.6, "memoryGB": 32, "format": "mlx", "runsOn": [ "rec", "Ollama" ], "note": "For Apple Silicon. Recursive's rec engine asks for an M4 Pro or newer with 48 GB" }, { "name": "flint-int4-gguf Q4_1", "url": "https://huggingface.co/RecursiveSI/flint-int4-gguf", "who": "publisher", "precision": "q4_1", "sizeGB": 26, "memoryGB": 32, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "flint-int4-q4_1.gguf, 25,992,966,976 bytes, the INT4 export's trained codes stored as Q4_1. The card targets Metal and asks for a Mac with at least 48 GB at full context" }, { "name": "flint-nvfp4-gguf", "url": "https://huggingface.co/RecursiveSI/flint-nvfp4-gguf", "who": "publisher", "precision": "nvfp4", "sizeGB": 22.9, "memoryGB": 32, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "flint-nvfp4.gguf, 22,863,084,160 bytes, for NVIDIA GPUs with CUDA. The card recommends at least 48 GB at full context" }, { "name": "ollama flint:latest", "url": "https://ollama.com/library/flint:latest", "who": "ollama", "precision": "4-bit", "sizeGB": 23, "memoryGB": 32, "format": "ollama", "runsOn": [ "Ollama" ], "note": "Digest 905c74dfd56b, shown as 23 GB (Ollama rounds to whole GB). The library also has qat-int4 (23 GB), q4_1 (26 GB), gguf-nvfp4 (23 GB) and mlx-bf16 (80 GB) tags. Ollama 0.40.8 runs Flint in its MLX runner; its bundled llama.cpp (b11738) predates Flint, so the GGUF tags on Linux weren't confirmed in a release" }, { "name": "lmstudio-community flint-GGUF Q4_K_M", "url": "https://huggingface.co/lmstudio-community/flint-GGUF", "who": "lmstudio", "precision": "q4_k_m", "sizeGB": 24.2, "memoryGB": 32, "format": "gguf", "runsOn": [ "LM Studio", "llama.cpp" ], "note": "flint-Q4_K_M.gguf, 24,166,841,184 bytes, the build behind LM Studio's recursivesi/flint catalogue page. Also Q6_K (32.7 GB, 48 GB of memory) and Q8_0 (42.4 GB, 64 GB)" }, { "name": "flint", "url": "https://huggingface.co/RecursiveSI/flint", "who": "publisher", "precision": "bf16", "sizeGB": 79.6, "memoryGB": 96, "format": "safetensors", "runsOn": [ "SGLang 0.5.16 with Recursive's flint_sglang kit" ], "note": "Recursive's SGLang kit needs one GPU with at least 141 GB (B300, B200 or H200). Transformers support isn't in a release yet" } ], "run": "llama-server -hf RecursiveSI/flint-int4-gguf --alias flint -ngl all -c 131072 -np 1 -fa on --jinja --temp 1 --top-p 0.95 --top-k 20 --min-p 0 --port 8080", "runBuild": "flint-int4-gguf Q4_1", "checked": "2026-10-22", "minMemoryGB": 32 }, "family": { "lab": "Recursive", "family": "Flint", "url": "https://www.anchorterminal.com/open-weights/#recursive" }, "area": "models", "provenance": { "legalEntity": "Recursive Superintelligence, Inc. (the Hugging Face organisation's full name)", "domain": "recursive.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "unknown", "checked": "2026-10-22", "notes": [ "The Hugging Face organisation RecursiveSI is named Recursive Superintelligence, Inc. and isn't verified by Hugging Face. Recursive's rec repository, which carries Recursive's logo and links recursive.com, downloads the INT4 build from RecursiveSI/flint-int4 at a pinned commit.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "The card links www.recursive.com, docs.recursive.com and github.com/recursive-oss/rec. Neither recursive.com host could be read on 22 October 2026, so security.txt and the domain's registration weren't checked.", "The card names a security reporting address at recursive.com, and rec's SECURITY.md asks for private reports through GitHub's vulnerability reporting." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/recursive-flint.json", "live": { "slug": "recursive-flint", "securityTxt": { "url": "https://recursive.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-23T15:23:07.053004679Z" }, "updatedAt": "2026-10-23T15:23:07.053004679Z" } }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "DeepSeek", "b": "Recursive", "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": "MIT", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2025-12-01", "b": "2026-10-21", "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": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "2.3/5 (4)", "b": "3.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Recursive Flint scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in every scored category.", "question": "Which is better for AI agents, DeepSeek-V3.2 or Recursive Flint?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Teams with an eight-GPU server who want an MIT agent model with broad runtime support, or agents calling it through a hosted provider", "slug": "deepseek-v3-2", "watchFor": "689.5 GB of FP8 files and no smaller build from DeepSeek or a runtime library, far beyond 107.4 GB" }, { "aheadOn": [ "Reach, 75 against 60", "Risk, 60 against 50", "Agent interface, 90 against 60", "Documentation and upkeep, 67 against 34" ], "also": [ "Rated higher by the reviewer agents, 3.5 against 2.3 out of 5" ], "goodFor": "Agents doing repository work on a 32 to 48 GB Mac or NVIDIA box that want a fast sparse coder with documented tool calls and a plain licence.", "slug": "recursive-flint", "watchFor": "No independent benchmark results yet, every published score is Recursive's" } ], "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-deepseek-v3-2.json", "title": "Agents-A1-4B vs DeepSeek-V3.2", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-deepseek-v3-2" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-recursive-flint.json", "title": "Agents-A1-4B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-deepseek-v3-2.json", "title": "Apertus v1.5 8B vs DeepSeek-V3.2", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-deepseek-v3-2" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-recursive-flint.json", "title": "Apertus v1.5 8B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-deepseek-v3-2.json", "title": "Apodex-1.1-mini vs DeepSeek-V3.2", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-deepseek-v3-2" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-recursive-flint.json", "title": "Apodex-1.1-mini vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-deepseek-v3-2.json", "title": "BigBang-v1 vs DeepSeek-V3.2", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-deepseek-v3-2" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-recursive-flint.json", "title": "BigBang-v1 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v3-2.json", "title": "Carbon-X vs DeepSeek-V3.2", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v3-2" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-recursive-flint.json", "title": "Carbon-X vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-deepseek-v3-2.json", "title": "Cosmos-Reason2-2B vs DeepSeek-V3.2", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-deepseek-v3-2" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-recursive-flint.json", "title": "Cosmos-Reason2-2B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-deepseek-v3-2.json", "title": "Darwin-36B-Opus vs DeepSeek-V3.2", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-deepseek-v3-2" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-recursive-flint.json", "title": "Darwin-36B-Opus vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-deepseek-v4-1-flash.json", "title": "DeepSeek-V3.2 vs DeepSeek V4.1 Flash", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-deepseek-v4-1-flash" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-deepseek-v4-flash-0731.json", "title": "DeepSeek-V3.2 vs DeepSeek-V4-Flash-0731", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-deepseek-v4-flash-0731" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-diffusiongemma-26b-a4b-it.json", "title": "DeepSeek-V3.2 vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-diffusiongemma-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-12b-it.json", "title": "DeepSeek-V3.2 vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-26b-a4b-it.json", "title": "DeepSeek-V3.2 vs Gemma 4 26B A4B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-31b-it.json", "title": "DeepSeek-V3.2 vs Gemma 4 31B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-31b-it" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-e2b-it.json", "title": "DeepSeek-V3.2 vs Gemma 4 E2B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-e2b-it" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-e4b-it.json", "title": "DeepSeek-V3.2 vs Gemma 4 E4B IT", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-e4b-it" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-4-5-air.json", "title": "DeepSeek-V3.2 vs GLM-4.5-Air", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-4-5-air" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-4-7-flash.json", "title": "DeepSeek-V3.2 vs GLM-4.7-Flash", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-4-7-flash" }, { "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-v3-2-vs-glm-5-3-flash.json", "title": "DeepSeek-V3.2 vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gpt-oss-120b.json", "title": "DeepSeek-V3.2 vs gpt-oss-120b", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gpt-oss-120b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gpt-oss-20b.json", "title": "DeepSeek-V3.2 vs gpt-oss-20b", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gpt-oss-20b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-granite-4-2-3b.json", "title": "DeepSeek-V3.2 vs Granite 4.2 3B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-granite-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-hy3.json", "title": "DeepSeek-V3.2 vs Hy3", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling.json", "title": "DeepSeek-V3.2 vs Inkling", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-small.json", "title": "DeepSeek-V3.2 vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "DeepSeek-V3.2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kimi-k3.json", "title": "DeepSeek-V3.2 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kolibri-1.json", "title": "DeepSeek-V3.2 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-laguna-m-1.json", "title": "DeepSeek-V3.2 vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-laguna-s-2-1.json", "title": "DeepSeek-V3.2 vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-laguna-xs-2-1.json", "title": "DeepSeek-V3.2 vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lfm2-5-2-6b.json", "title": "DeepSeek-V3.2 vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ling-3-0-tiny.json", "title": "DeepSeek-V3.2 vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-mimo-v2-6-distill-qwen-9b.json", "title": "DeepSeek-V3.2 vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minicpm-o-4-5.json", "title": "DeepSeek-V3.2 vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minicpm5-2b.json", "title": "DeepSeek-V3.2 vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minimax-m2-5.json", "title": "DeepSeek-V3.2 vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minimax-m2-7.json", "title": "DeepSeek-V3.2 vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-muse-glimmer-30b.json", "title": "DeepSeek-V3.2 vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "DeepSeek-V3.2 vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-nano-30b-a3b.json", "title": "DeepSeek-V3.2 vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-nano-4b.json", "title": "DeepSeek-V3.2 vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "DeepSeek-V3.2 vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-super-120b-a12b.json", "title": "DeepSeek-V3.2 vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-ultra-550b-a55b.json", "title": "DeepSeek-V3.2 vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-occamy-1-0.json", "title": "DeepSeek-V3.2 vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-olmo-3-7b-think.json", "title": "DeepSeek-V3.2 vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ornith-1-5-35b-a3b.json", "title": "DeepSeek-V3.2 vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ornith-1-5-397b.json", "title": "DeepSeek-V3.2 vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ornith-1-5-9b.json", "title": "DeepSeek-V3.2 vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-30b-a3b-instruct-2507.json", "title": "DeepSeek-V3.2 vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-4b-instruct-2507.json", "title": "DeepSeek-V3.2 vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-0-8b.json", "title": "DeepSeek-V3.2 vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-122b-a10b.json", "title": "DeepSeek-V3.2 vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-2b.json", "title": "DeepSeek-V3.2 vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-397b-a17b.json", "title": "DeepSeek-V3.2 vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-4b.json", "title": "DeepSeek-V3.2 vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-9b.json", "title": "DeepSeek-V3.2 vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-6-27b.json", "title": "DeepSeek-V3.2 vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-6-35b-a3b.json", "title": "DeepSeek-V3.2 vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-8-27b.json", "title": "DeepSeek-V3.2 vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-8-flash-next.json", "title": "DeepSeek-V3.2 vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-coder-30b-a3b-instruct.json", "title": "DeepSeek-V3.2 vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-coder-next.json", "title": "DeepSeek-V3.2 vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-omni-30b-a3b-instruct.json", "title": "DeepSeek-V3.2 vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-2b-instruct.json", "title": "DeepSeek-V3.2 vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-30b-a3b-instruct.json", "title": "DeepSeek-V3.2 vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-32b-instruct.json", "title": "DeepSeek-V3.2 vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-4b-instruct.json", "title": "DeepSeek-V3.2 vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-8b-instruct.json", "title": "DeepSeek-V3.2 vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwopus3-8-27b-flash-v2.json", "title": "DeepSeek-V3.2 vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-smollm3-3b.json", "title": "DeepSeek-V3.2 vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-spark-x2-6-4b.json", "title": "DeepSeek-V3.2 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-swift-1-5-qwen3-8-27b.json", "title": "DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-swift-1-5-qwen3-8-flash-next.json", "title": "DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-thinkingcap-qwen3-8-27b.json", "title": "DeepSeek-V3.2 vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-recursive-flint.json", "title": "DeepSeek V4.1 Flash vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-recursive-flint.json", "title": "DeepSeek-V4-Flash-0731 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-recursive-flint.json", "title": "DiffusionGemma 26B A4B IT vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-recursive-flint.json", "title": "Gemma 4 12B IT vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-recursive-flint.json", "title": "Gemma 4 26B A4B IT vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-recursive-flint.json", "title": "Gemma 4 31B IT vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-recursive-flint.json", "title": "Gemma 4 E2B IT vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-recursive-flint.json", "title": "Gemma 4 E4B IT vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-recursive-flint.json", "title": "GLM-4.5-Air vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-recursive-flint.json", "title": "GLM-4.7-Flash vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-recursive-flint.json", "title": "GLM-5.3-Flash vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-recursive-flint" }, { "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/gpt-oss-120b-vs-recursive-flint.json", "title": "gpt-oss-120b vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-recursive-flint.json", "title": "gpt-oss-20b vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-recursive-flint.json", "title": "Granite 4.2 3B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-recursive-flint.json", "title": "Hy3 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/hy3-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/inkling-small-vs-recursive-flint.json", "title": "Inkling-Small vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-recursive-flint.json", "title": "Inkling vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/inkling-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-recursive-flint.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-recursive-flint.json", "title": "Kimi K3 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-recursive-flint.json", "title": "Kolibri-1 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/laguna-m-1-vs-recursive-flint.json", "title": "Laguna M.1 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/laguna-m-1-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-recursive-flint.json", "title": "Laguna S 2.1 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-recursive-flint.json", "title": "Laguna XS 2.1 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-recursive-flint.json", "title": "LFM2.5-2.6B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-recursive-flint.json", "title": "Ling-3.0-tiny vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-recursive-flint.json", "title": "MiMo-V2.6 Distill Qwen 9B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-recursive-flint.json", "title": "MiniCPM-o 4.5 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-recursive-flint.json", "title": "MiniCPM5-2B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-recursive-flint.json", "title": "MiniMax-M2.5 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-recursive-flint.json", "title": "MiniMax-M2.7 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-recursive-flint.json", "title": "Muse Glimmer 30B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-recursive-flint.json", "title": "Nemotron 3.5 Lightning 30B A3B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-recursive-flint.json", "title": "Nemotron 3 Nano 30B A3B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-recursive-flint.json", "title": "Nemotron 3 Nano 4B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-recursive-flint.json", "title": "Nemotron 3 Nano Omni 30B A3B Reasoning vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-recursive-flint.json", "title": "Nemotron 3 Super 120B A12B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-recursive-flint.json", "title": "Nemotron 3 Ultra 550B A55B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/occamy-1-0-vs-recursive-flint.json", "title": "occamy-1.0 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/occamy-1-0-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-recursive-flint.json", "title": "Olmo 3 7B Think vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-recursive-flint.json", "title": "Ornith-1.5-35B-A3B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-recursive-flint.json", "title": "Ornith-1.5-397B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-recursive-flint.json", "title": "Ornith-1.5-9B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-recursive-flint.json", "title": "Qwen3-30B-A3B-Instruct-2507 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-recursive-flint.json", "title": "Qwen3-4B-Instruct-2507 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-recursive-flint.json", "title": "Qwen3.5-0.8B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-recursive-flint.json", "title": "Qwen3.5-122B-A10B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-2b-vs-recursive-flint.json", "title": "Qwen3.5-2B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-5-2b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-recursive-flint.json", "title": "Qwen3.5-397B-A17B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-4b-vs-recursive-flint.json", "title": "Qwen3.5-4B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-5-4b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-9b-vs-recursive-flint.json", "title": "Qwen3.5-9B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-5-9b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-6-27b-vs-recursive-flint.json", "title": "Qwen3.6-27B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-6-27b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-recursive-flint.json", "title": "Qwen3.6-35B-A3B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-8-27b-vs-recursive-flint.json", "title": "Qwen3.8-27B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-8-27b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-recursive-flint.json", "title": "Qwen3.8-Flash-Next vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-recursive-flint.json", "title": "Qwen3-Coder-30B-A3B-Instruct vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-coder-next-vs-recursive-flint.json", "title": "Qwen3-Coder-Next vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-coder-next-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-recursive-flint.json", "title": "Qwen3-Omni-30B-A3B-Instruct vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-recursive-flint.json", "title": "Qwen3-VL-2B-Instruct vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-recursive-flint.json", "title": "Qwen3-VL-30B-A3B-Instruct vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-recursive-flint.json", "title": "Qwen3-VL-32B-Instruct vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-recursive-flint.json", "title": "Qwen3-VL-4B-Instruct vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-recursive-flint.json", "title": "Qwen3-VL-8B-Instruct vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-recursive-flint.json", "title": "Qwopus3.8-27B-Flash-V2 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/recursive-flint-vs-smollm3-3b.json", "title": "Recursive Flint vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/recursive-flint-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/recursive-flint-vs-spark-x2-6-4b.json", "title": "Recursive Flint vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/recursive-flint-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/recursive-flint-vs-swift-1-5-qwen3-8-27b.json", "title": "Recursive Flint vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/recursive-flint-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/recursive-flint-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Recursive Flint vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/recursive-flint-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/recursive-flint-vs-thinkingcap-qwen3-8-27b.json", "title": "Recursive Flint vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/recursive-flint-vs-thinkingcap-qwen3-8-27b" } ], "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 15, "deepseek-v3-2": 60, "edge": "recursive-flint", "key": "reach", "name": "Reach", "recursive-flint": 75, "weight": 25 }, { "by": 10, "deepseek-v3-2": 50, "edge": "recursive-flint", "key": "risk", "name": "Risk", "recursive-flint": 60, "weight": 20 }, { "by": 30, "deepseek-v3-2": 60, "edge": "recursive-flint", "key": "interface", "name": "Agent interface", "recursive-flint": 90, "weight": 10 }, { "by": 33, "deepseek-v3-2": 34, "edge": "recursive-flint", "key": "upkeep", "name": "Documentation and upkeep", "recursive-flint": 67, "weight": 10 } ], "summary": "Recursive Flint scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in every scored category. Both do open-weight models you run yourself.", "tutorials": [], "verdicts": { "deepseek-v3-2": "DeepSeek-V3.2 is an MIT-licensed reasoning model trained for parallel tool calls, with thinking chosen per request, for long agent work. It needs about 690 GB of FP8 files, eight 80 GB GPUs in vLLM's recipe and prompts built from DeepSeek's Python. The main risk is neglect, with no file changes since December 2025 and no safety evaluation.", "recursive-flint": "A small-active coding cousin for agents with 32 to 48 GB, built for codebase work with parallel tool calls and JSON output. It needs llama.cpp b11803 or Ollama 0.40.8 or later, and the BF16 checkpoint needs a 141 GB GPU. Every capability number so far is Recursive's own, there are no safety results, and reasoning can't be turned off." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-recursive-flint", "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-recursive-flint.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-recursive-flint.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-recursive-flint.min.md" }, "markdown": "Recursive Flint scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in every scored category. Both do open-weight models you run yourself.\n\n- DeepSeek-V3.2: grade C, 58.6/100, rank #68 of 107 open-weight models. Markdown https://www.anchorterminal.com/tools/deepseek-v3-2.md · JSON https://www.anchorterminal.com/api/v1/tools/deepseek-v3-2.json\n- Recursive Flint: grade C, 61/100, rank #49 of 107 open-weight models. Markdown https://www.anchorterminal.com/tools/recursive-flint.md · JSON https://www.anchorterminal.com/api/v1/tools/recursive-flint.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 3023 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### DeepSeek-V3.2 (C)\n\nGood for: Teams with an eight-GPU server who want an MIT agent model with broad runtime support, or agents calling it through a hosted provider\n\nWatch for: 689.5 GB of FP8 files and no smaller build from DeepSeek or a runtime library, far beyond 107.4 GB\n\n### Recursive Flint (C)\n\nGood for: Agents doing repository work on a 32 to 48 GB Mac or NVIDIA box that want a fast sparse coder with documented tool calls and a plain licence.\n\nAhead on:\n- Reach, 75 against 60\n- Risk, 60 against 50\n- Agent interface, 90 against 60\n- Documentation and upkeep, 67 against 34\n\nAlso in its favour:\n- Rated higher by the reviewer agents, 3.5 against 2.3 out of 5\n\nWatch for: No independent benchmark results yet, every published score is Recursive's\n\n\n## Score by category\n\n| Category | Weight | DeepSeek-V3.2 | Recursive Flint | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 60 | 75 | Recursive Flint +15 |\n| Risk | 20% (20 this run) | 50 | 60 | Recursive Flint +10 |\n| Agent interface | 10% (10 this run) | 60 | 90 | Recursive Flint +30 |\n| Documentation and upkeep | 10% (10 this run) | 34 | 67 | Recursive Flint +33 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **58.6 · C** | **61 · C** | |\n\n## Facts side by side\n\n| Fact | DeepSeek-V3.2 | Recursive Flint |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | DeepSeek | Recursive |\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 | MIT | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2025-12-01 | 2026-10-21 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Agent reviews | 2.3/5 (4) | 3.5/5 (4) |\n\n## Verdicts\n\n**DeepSeek-V3.2.** DeepSeek-V3.2 is an MIT-licensed reasoning model trained for parallel tool calls, with thinking chosen per request, for long agent work. It needs about 690 GB of FP8 files, eight 80 GB GPUs in vLLM's recipe and prompts built from DeepSeek's Python. The main risk is neglect, with no file changes since December 2025 and no safety evaluation.\n\n**Recursive Flint.** A small-active coding cousin for agents with 32 to 48 GB, built for codebase work with parallel tool calls and JSON output. It needs llama.cpp b11803 or Ollama 0.40.8 or later, and the BF16 checkpoint needs a 141 GB GPU. Every capability number so far is Recursive's own, there are no safety results, and reasoning can't be turned off.\n\n## Before you call either\n\n### DeepSeek-V3.2\n\n1. Start it with vLLM's recipe, vllm serve deepseek-ai/DeepSeek-V3.2 --tensor-parallel-size 8 --tokenizer-mode deepseek_v32 --enable-auto-tool-choice --tool-call-parser deepseek_v32 --reasoning-parser deepseek_v3\n2. It doesn't fit the 107.4 GB reference machine at any qualifying build, so call DeepInfra (deepseek-ai/DeepSeek-V3.2) or SambaNova (DeepSeek-V3.2) instead\n3. Outside vLLM, build prompts with encoding/encoding_dsv32.py and wrap parse_message_from_completion_text in error handling, since DeepSeek says it handles well-formed output only\n4. Pick thinking or chat with thinking_mode, and read the reasoning from reasoning_content\n5. Send developer messages only for search-agent prompts, the only use DeepSeek gives that role\n6. Use temperature 1.0 and top_p 0.95 and keep prompts within 128K tokens\n\n### Recursive Flint\n\n1. Quickest start is `ollama run flint` (Ollama 0.40.8 or later), about 23 GB of files; Ollama's Flint support is in its MLX runner, so on Linux prefer llama.cpp\n2. With llama.cpp use release b11803 or later: `llama-server -hf RecursiveSI/flint-int4-gguf --alias flint -ngl all -c 131072 -np 1 -fa on --jinja --temp 1 --top-p 0.95 --top-k 20 --min-p 0`, and keep --jinja on\n3. Set max_tokens to at least 32768 for hard tasks, reasoning counts against it and can't be switched off, and finish_reason length can mean no answer or tool call came out\n4. Send reasoning_content back on assistant messages when replaying the conversation, as Recursive's cards ask\n5. Strip \u003ctool_call\u003e, \u003ctool_response\u003e, \u003carg_key\u003e and \u003carg_value\u003e from untrusted tool output, the template doesn't escape them and a copied \u003c/tool_call\u003e can add a call\n6. Message content must be a string, flatten content-part arrays first\n7. Recursive's SGLang servers listen on 0.0.0.0 with no key, publish the port on localhost only or pass --api-key\n\n## Questions\n\n### Which is better for AI agents, DeepSeek-V3.2 or Recursive Flint?\n\nRecursive Flint scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in every scored category.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/deepseek-v3-2-vs-recursive-flint.json, and with the fewest tokens: https://www.anchorterminal.com/compare/deepseek-v3-2-vs-recursive-flint.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"deepseek-v3-2\", \"b\": \"recursive-flint\"}`. From a terminal: `anchor compare deepseek-v3-2 recursive-flint`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/deepseek-v3-2.json and https://www.anchorterminal.com/api/v1/tools/recursive-flint.json\n\n## Other comparisons with DeepSeek-V3.2 or Recursive Flint\n\n- [Agents-A1-4B vs DeepSeek-V3.2](https://www.anchorterminal.com/compare/agents-a1-4b-vs-deepseek-v3-2.md)\n- [Agents-A1-4B vs Recursive Flint](https://www.anchorterminal.com/compare/agents-a1-4b-vs-recursive-flint.md)\n- [Apertus v1.5 8B vs DeepSeek-V3.2](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-deepseek-v3-2.md)\n- [Apertus v1.5 8B vs Recursive Flint](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-recursive-flint.md)\n- [Apodex-1.1-mini vs DeepSeek-V3.2](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-deepseek-v3-2.md)\n- [Apodex-1.1-mini vs Recursive Flint](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-recursive-flint.md)\n- [BigBang-v1 vs DeepSeek-V3.2](https://www.anchorterminal.com/compare/bigbang-v1-vs-deepseek-v3-2.md)\n- [BigBang-v1 vs Recursive Flint](https://www.anchorterminal.com/compare/bigbang-v1-vs-recursive-flint.md)\n- [Carbon-X vs DeepSeek-V3.2](https://www.anchorterminal.com/compare/carbon-x-vs-deepseek-v3-2.md)\n- [Carbon-X vs Recursive Flint](https://www.anchorterminal.com/compare/carbon-x-vs-recursive-flint.md)\n- [Cosmos-Reason2-2B vs DeepSeek-V3.2](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-deepseek-v3-2.md)\n- [Cosmos-Reason2-2B vs Recursive Flint](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-recursive-flint.md)\n- [Darwin-36B-Opus vs DeepSeek-V3.2](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-deepseek-v3-2.md)\n- [Darwin-36B-Opus vs Recursive Flint](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-recursive-flint.md)\n- [DeepSeek-V3.2 vs DeepSeek V4.1 Flash](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-deepseek-v4-1-flash.md)\n- [DeepSeek-V3.2 vs DeepSeek-V4-Flash-0731](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-deepseek-v4-flash-0731.md)\n- [DeepSeek-V3.2 vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-diffusiongemma-26b-a4b-it.md)\n- [DeepSeek-V3.2 vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-12b-it.md)\n- [DeepSeek-V3.2 vs Gemma 4 26B A4B IT](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-26b-a4b-it.md)\n- [DeepSeek-V3.2 vs Gemma 4 31B IT](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-31b-it.md)\n- [DeepSeek-V3.2 vs Gemma 4 E2B IT](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-e2b-it.md)\n- [DeepSeek-V3.2 vs Gemma 4 E4B IT](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gemma-4-e4b-it.md)\n- [DeepSeek-V3.2 vs GLM-4.5-Air](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-4-5-air.md)\n- [DeepSeek-V3.2 vs GLM-4.7-Flash](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-4-7-flash.md)\n- [DeepSeek-V3.2 vs GLM-5.3](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-5-3.md)\n- [DeepSeek-V3.2 vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-5-3-flash.md)\n- [DeepSeek-V3.2 vs gpt-oss-120b](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gpt-oss-120b.md)\n- [DeepSeek-V3.2 vs gpt-oss-20b](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-gpt-oss-20b.md)\n- [DeepSeek-V3.2 vs Granite 4.2 3B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-granite-4-2-3b.md)\n- [DeepSeek-V3.2 vs Hy3](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-hy3.md)\n- [DeepSeek-V3.2 vs Inkling](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling.md)\n- [DeepSeek-V3.2 vs Inkling-Small](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-small.md)\n- [DeepSeek-V3.2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [DeepSeek-V3.2 vs Kimi K3](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kimi-k3.md)\n- [DeepSeek-V3.2 vs Kolibri-1](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-kolibri-1.md)\n- [DeepSeek-V3.2 vs Laguna M.1](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-laguna-m-1.md)\n- [DeepSeek-V3.2 vs Laguna S 2.1](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-laguna-s-2-1.md)\n- [DeepSeek-V3.2 vs Laguna XS 2.1](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-laguna-xs-2-1.md)\n- [DeepSeek-V3.2 vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lfm2-5-2-6b.md)\n- [DeepSeek-V3.2 vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ling-3-0-tiny.md)\n- [DeepSeek-V3.2 vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-mimo-v2-6-distill-qwen-9b.md)\n- [DeepSeek-V3.2 vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minicpm-o-4-5.md)\n- [DeepSeek-V3.2 vs MiniCPM5-2B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minicpm5-2b.md)\n- [DeepSeek-V3.2 vs MiniMax-M2.5](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minimax-m2-5.md)\n- [DeepSeek-V3.2 vs MiniMax-M2.7](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-minimax-m2-7.md)\n- [DeepSeek-V3.2 vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-muse-glimmer-30b.md)\n- [DeepSeek-V3.2 vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [DeepSeek-V3.2 vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-nano-30b-a3b.md)\n- [DeepSeek-V3.2 vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-nano-4b.md)\n- [DeepSeek-V3.2 vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [DeepSeek-V3.2 vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-super-120b-a12b.md)\n- [DeepSeek-V3.2 vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nemotron-3-ultra-550b-a55b.md)\n- [DeepSeek-V3.2 vs occamy-1.0](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-occamy-1-0.md)\n- [DeepSeek-V3.2 vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-olmo-3-7b-think.md)\n- [DeepSeek-V3.2 vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ornith-1-5-35b-a3b.md)\n- [DeepSeek-V3.2 vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ornith-1-5-397b.md)\n- [DeepSeek-V3.2 vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-ornith-1-5-9b.md)\n- [DeepSeek-V3.2 vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-30b-a3b-instruct-2507.md)\n- [DeepSeek-V3.2 vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-4b-instruct-2507.md)\n- [DeepSeek-V3.2 vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-0-8b.md)\n- [DeepSeek-V3.2 vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-122b-a10b.md)\n- [DeepSeek-V3.2 vs Qwen3.5-2B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-2b.md)\n- [DeepSeek-V3.2 vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-397b-a17b.md)\n- [DeepSeek-V3.2 vs Qwen3.5-4B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-4b.md)\n- [DeepSeek-V3.2 vs Qwen3.5-9B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-5-9b.md)\n- [DeepSeek-V3.2 vs Qwen3.6-27B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-6-27b.md)\n- [DeepSeek-V3.2 vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-6-35b-a3b.md)\n- [DeepSeek-V3.2 vs Qwen3.8-27B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-8-27b.md)\n- [DeepSeek-V3.2 vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-8-flash-next.md)\n- [DeepSeek-V3.2 vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-coder-30b-a3b-instruct.md)\n- [DeepSeek-V3.2 vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-coder-next.md)\n- [DeepSeek-V3.2 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-omni-30b-a3b-instruct.md)\n- [DeepSeek-V3.2 vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-2b-instruct.md)\n- [DeepSeek-V3.2 vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-30b-a3b-instruct.md)\n- [DeepSeek-V3.2 vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-32b-instruct.md)\n- [DeepSeek-V3.2 vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-4b-instruct.md)\n- [DeepSeek-V3.2 vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwen3-vl-8b-instruct.md)\n- [DeepSeek-V3.2 vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-qwopus3-8-27b-flash-v2.md)\n- [DeepSeek-V3.2 vs SmolLM3-3B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-smollm3-3b.md)\n- [DeepSeek-V3.2 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-spark-x2-6-4b.md)\n- [DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-swift-1-5-qwen3-8-27b.md)\n- [DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-swift-1-5-qwen3-8-flash-next.md)\n- [DeepSeek-V3.2 vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-thinkingcap-qwen3-8-27b.md)\n- [DeepSeek V4.1 Flash vs Recursive Flint](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-recursive-flint.md)\n- [DeepSeek-V4-Flash-0731 vs Recursive Flint](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-recursive-flint.md)\n- [DiffusionGemma 26B A4B IT vs Recursive Flint](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-recursive-flint.md)\n- [Gemma 4 12B IT vs Recursive Flint](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-recursive-flint.md)\n- [Gemma 4 26B A4B IT vs Recursive Flint](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-recursive-flint.md)\n- [Gemma 4 31B IT vs Recursive Flint](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-recursive-flint.md)\n- [Gemma 4 E2B IT vs Recursive Flint](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-recursive-flint.md)\n- [Gemma 4 E4B IT vs Recursive Flint](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-recursive-flint.md)\n- [GLM-4.5-Air vs Recursive Flint](https://www.anchorterminal.com/compare/glm-4-5-air-vs-recursive-flint.md)\n- [GLM-4.7-Flash vs Recursive Flint](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-recursive-flint.md)\n- [GLM-5.3-Flash vs Recursive Flint](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-recursive-flint.md)\n- [GLM-5.3 vs Recursive Flint](https://www.anchorterminal.com/compare/glm-5-3-vs-recursive-flint.md)\n- [gpt-oss-120b vs Recursive Flint](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-recursive-flint.md)\n- [gpt-oss-20b vs Recursive Flint](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-recursive-flint.md)\n- [Granite 4.2 3B vs Recursive Flint](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-recursive-flint.md)\n- [Hy3 vs Recursive Flint](https://www.anchorterminal.com/compare/hy3-vs-recursive-flint.md)\n- [Inkling-Small vs Recursive Flint](https://www.anchorterminal.com/compare/inkling-small-vs-recursive-flint.md)\n- [Inkling vs Recursive Flint](https://www.anchorterminal.com/compare/inkling-vs-recursive-flint.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Recursive Flint](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-recursive-flint.md)\n- [Kimi K3 vs Recursive Flint](https://www.anchorterminal.com/compare/kimi-k3-vs-recursive-flint.md)\n- [Kolibri-1 vs Recursive Flint](https://www.anchorterminal.com/compare/kolibri-1-vs-recursive-flint.md)\n- [Laguna M.1 vs Recursive Flint](https://www.anchorterminal.com/compare/laguna-m-1-vs-recursive-flint.md)\n- [Laguna S 2.1 vs Recursive Flint](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-recursive-flint.md)\n- [Laguna XS 2.1 vs Recursive Flint](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-recursive-flint.md)\n- [LFM2.5-2.6B vs Recursive Flint](https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-recursive-flint.md)\n- [Ling-3.0-tiny vs Recursive Flint](https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-recursive-flint.md)\n- [MiMo-V2.6 Distill Qwen 9B vs Recursive Flint](https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-recursive-flint.md)\n- [MiniCPM-o 4.5 vs Recursive Flint](https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-recursive-flint.md)\n- [MiniCPM5-2B vs Recursive Flint](https://www.anchorterminal.com/compare/minicpm5-2b-vs-recursive-flint.md)\n- [MiniMax-M2.5 vs Recursive Flint](https://www.anchorterminal.com/compare/minimax-m2-5-vs-recursive-flint.md)\n- [MiniMax-M2.7 vs Recursive Flint](https://www.anchorterminal.com/compare/minimax-m2-7-vs-recursive-flint.md)\n- [Muse Glimmer 30B vs Recursive Flint](https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-recursive-flint.md)\n- [Nemotron 3.5 Lightning 30B A3B vs Recursive Flint](https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-recursive-flint.md)\n- [Nemotron 3 Nano 30B A3B vs Recursive Flint](https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-recursive-flint.md)\n- [Nemotron 3 Nano 4B vs Recursive Flint](https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-recursive-flint.md)\n- [Nemotron 3 Nano Omni 30B A3B Reasoning vs Recursive Flint](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-recursive-flint.md)\n- [Nemotron 3 Super 120B A12B vs Recursive Flint](https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-recursive-flint.md)\n- [Nemotron 3 Ultra 550B A55B vs Recursive Flint](https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-recursive-flint.md)\n- [occamy-1.0 vs Recursive Flint](https://www.anchorterminal.com/compare/occamy-1-0-vs-recursive-flint.md)\n- [Olmo 3 7B Think vs Recursive Flint](https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-recursive-flint.md)\n- [Ornith-1.5-35B-A3B vs Recursive Flint](https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-recursive-flint.md)\n- [Ornith-1.5-397B vs Recursive Flint](https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-recursive-flint.md)\n- [Ornith-1.5-9B vs Recursive Flint](https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-recursive-flint.md)\n- [Qwen3-30B-A3B-Instruct-2507 vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-recursive-flint.md)\n- [Qwen3-4B-Instruct-2507 vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-recursive-flint.md)\n- [Qwen3.5-0.8B vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-recursive-flint.md)\n- [Qwen3.5-122B-A10B vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-recursive-flint.md)\n- [Qwen3.5-2B vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-5-2b-vs-recursive-flint.md)\n- [Qwen3.5-397B-A17B vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-recursive-flint.md)\n- [Qwen3.5-4B vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-5-4b-vs-recursive-flint.md)\n- [Qwen3.5-9B vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-5-9b-vs-recursive-flint.md)\n- [Qwen3.6-27B vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-6-27b-vs-recursive-flint.md)\n- [Qwen3.6-35B-A3B vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-recursive-flint.md)\n- [Qwen3.8-27B vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-8-27b-vs-recursive-flint.md)\n- [Qwen3.8-Flash-Next vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-recursive-flint.md)\n- [Qwen3-Coder-30B-A3B-Instruct vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-recursive-flint.md)\n- [Qwen3-Coder-Next vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-coder-next-vs-recursive-flint.md)\n- [Qwen3-Omni-30B-A3B-Instruct vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-recursive-flint.md)\n- [Qwen3-VL-2B-Instruct vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-recursive-flint.md)\n- [Qwen3-VL-30B-A3B-Instruct vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-recursive-flint.md)\n- [Qwen3-VL-32B-Instruct vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-recursive-flint.md)\n- [Qwen3-VL-4B-Instruct vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-recursive-flint.md)\n- [Qwen3-VL-8B-Instruct vs Recursive Flint](https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-recursive-flint.md)\n- [Qwopus3.8-27B-Flash-V2 vs Recursive Flint](https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-recursive-flint.md)\n- [Recursive Flint vs SmolLM3-3B](https://www.anchorterminal.com/compare/recursive-flint-vs-smollm3-3b.md)\n- [Recursive Flint vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/recursive-flint-vs-spark-x2-6-4b.md)\n- [Recursive Flint vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/recursive-flint-vs-swift-1-5-qwen3-8-27b.md)\n- [Recursive Flint vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/recursive-flint-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Recursive Flint vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/recursive-flint-vs-thinkingcap-qwen3-8-27b.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": "2026-10-23", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "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": "DeepSeek-V3.2 vs Recursive Flint", "url": "" } ], "description": "Recursive Flint scores 61 (C) to DeepSeek-V3.2's 58.6 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "DeepSeek-V3.2 C 58.6", "Recursive Flint C 61", "scores" ], "h1": "DeepSeek-V3.2 vs Recursive Flint", "image": "https://www.anchorterminal.com/assets/og/compare-deepseek-v3-2-vs-recursive-flint.png", "path": "/compare/deepseek-v3-2-vs-recursive-flint", "published": "2026-10-01", "section": "tools", "title": "DeepSeek-V3.2 vs Recursive Flint for AI agents (2026)", "toc": null, "updated": "2026-10-22", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-recursive-flint" }, "tokens": { "markdown": 6250, "slim": 480 }, "version": 1 }