{ "data": { "similar": [ { "grade": "BB", "json": "https://www.anchorterminal.com/tools/qwen3-embedding-8b.json", "name": "Qwen3-Embedding-8B", "score": 75.4, "shared": [ "model.open-weights" ], "slug": "qwen3-embedding-8b" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/gemma-4-31b-it.json", "name": "Gemma 4 31B IT", "score": 74.1, "shared": [ "model.open-weights" ], "slug": "gemma-4-31b-it" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/qwen3-embedding-4b.json", "name": "Qwen3-Embedding-4B", "score": 73.6, "shared": [ "model.open-weights" ], "slug": "qwen3-embedding-4b" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/gemma-4-12b-it.json", "name": "Gemma 4 12B IT", "score": 72.3, "shared": [ "model.open-weights" ], "slug": "gemma-4-12b-it" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.json", "name": "Gemma 4 26B A4B IT", "score": 72.2, "shared": [ "model.open-weights" ], "slug": "gemma-4-26b-a4b-it" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/gpt-oss-120b.json", "name": "gpt-oss-120b", "score": 70.2, "shared": [ "model.open-weights" ], "slug": "gpt-oss-120b" } ], "tool": { "slug": "north-mini-code-1-0", "name": "North Mini Code 1.0", "vendor": "Cohere", "vendorUrl": "https://cohere.com", "kind": "weights", "category": "open-weights", "summary": "North Mini Code 1.0 is Cohere's open-weight coding agent model, a mixture of experts of 30B parameters with 3B active, trained for tool use, with interleaved thinking and a 256K context. Apache 2.0. Cohere's 4-bit build is 19 GB.", "url": "https://www.anchorterminal.com/tools/north-mini-code-1-0", "markdownUrl": "https://www.anchorterminal.com/tools/north-mini-code-1-0.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/north-mini-code-1-0.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/north-mini-code-1-0.json", "dns": "north-mini-code-1-0.grade.anchorterminal.com", "repo": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "CohereLabs/North-Mini-Code-1.0" }, { "registry": "huggingface", "name": "CohereLabs/North-Mini-Code-1.0-fp8" }, { "registry": "huggingface", "name": "CohereLabs/North-Mini-Code-1.0-w4a16" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. None of the repositories is gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download and use under Apache 2.0. The card calls it a research release. Running it yourself takes 19.4 GB at 4 bits (w4a16), 32.1 GB in FP8 or 61.0 GB in BF16 (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/CohereLabs/North-Mini-Code-1.0", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "coding", "agentic", "reasoning", "tool-calling", "long-context", "apache-2.0", "safetensors", "fp8", "4-bit", "self-hosted" ], "lastRelease": "2026-07-29", "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": 63, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 85, "reach": 85, "risk": 60, "upkeep": 36 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "capability", "name": "Capability", "weight": 35, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending for this listing. Nobody independent has published results for it in at least two areas yet, so its weight is shared across the other four and the total is capped at 61 until they do or our own runs start." }, { "key": "reach", "name": "Reach", "weight": 25, "effectiveWeight": 38.46, "score": 85, "points": 32.69, "reason": "Memory 25, the smallest build from Cohere is the w4a16 repository, 19.38 GB, and 19.38 GB × 1.2 = 23.3 GB, within 24 GB. Unsloth's GGUF isn't read for this line. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the cohere2_moe model, and llama.cpp b12242 has the cohere2moe architecture. Builds 15, Quantised builds from Cohere at two precisions, FP8 and 4-bit weights (w4a16), each in its own repository. Terms 15, Apache 2.0 in the metadata and on the card, an OSI licence with nothing added. Download 10, the Hub API reports gated false for the model and its builds on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 25 + 20 + 15 + 15 + 10 + 0 = 85.", "checked": "2026-11-10" }, { "key": "risk", "name": "Risk", "weight": 20, "effectiveWeight": 30.77, "score": 60, "points": 18.46, "reason": "File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in Cohere's verified CohereLabs organisation, which cohere.com links to per our other Cohere listings (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, Cohere's trust centre holds a responsible disclosure policy with a bug bounty, as recorded on our Cohere listings (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.", "checked": "2026-11-10" }, { "key": "interface", "name": "Agent interface", "weight": 10, "effectiveWeight": 15.38, "score": 85, "points": 13.08, "reason": "Chat template 20, chat_template.jinja in the repository (12,397 characters). Tool-calling format 25, the card documents how tools are declared (JSON schema through the chat template), how the call and its thinking go back into the history and how results are appended, and names the cohere_command4 tool-call parser for vLLM, which released vLLM has. Trained tool calling 20, the card says the model was specifically trained with tool-use capabilities for agentic coding, with reinforcement learning on verifiable tasks, and the template renders every call in a turn with thinking between them. Structured output 0, JSON schema is for describing tools. Reasoning control 10, the template has a reasoning_effort setting, and the card names the cohere_command4 reasoning parser, which returns thinking apart from the answer. Context 10, 256K tokens per the card, with 64K of output, and 500,000 positions in config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.", "checked": "2026-11-10" }, { "key": "upkeep", "name": "Documentation and upkeep", "weight": 10, "effectiveWeight": 15.38, "score": 36, "points": 5.54, "reason": "Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, the card gives the training method and nothing about the data. Last change 10, the main repository last changed on 15 June 2026 (outdated chat templates removed), 148 days before this check, and the draft model's repository on 29 July, 104 days. Responsiveness 0, none of the 11 most recent discussions that aren't pull requests (7 June to 6 November 2026) has a reply from a CohereLabs member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, A first release, with each build in its own repository. File health 10, Config, template and card agree on the architecture, and the June commit that removed broken templates says so. 11 + 0 + 10 + 0 + 5 + 10 = 36.", "checked": "2026-11-10" } ], "assessment": { "date": "2026-11-10", "basis": "public evidence", "confidence": "low", "notes": { "capability": "Pending for this listing. Independent results were found in 0 areas (none), and Capability needs 2. Its weight is shared across the other four categories and the total is capped at 61 until there are more, or our own runs start.", "interface": "Chat template 20, chat_template.jinja in the repository (12,397 characters). Tool-calling format 25, the card documents how tools are declared (JSON schema through the chat template), how the call and its thinking go back into the history and how results are appended, and names the cohere_command4 tool-call parser for vLLM, which released vLLM has. Trained tool calling 20, the card says the model was specifically trained with tool-use capabilities for agentic coding, with reinforcement learning on verifiable tasks, and the template renders every call in a turn with thinking between them. Structured output 0, JSON schema is for describing tools. Reasoning control 10, the template has a reasoning_effort setting, and the card names the cohere_command4 reasoning parser, which returns thinking apart from the answer. Context 10, 256K tokens per the card, with 64K of output, and 500,000 positions in config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.", "reach": "Memory 25, the smallest build from Cohere is the w4a16 repository, 19.38 GB, and 19.38 GB × 1.2 = 23.3 GB, within 24 GB. Unsloth's GGUF isn't read for this line. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the cohere2_moe model, and llama.cpp b12242 has the cohere2moe architecture. Builds 15, Quantised builds from Cohere at two precisions, FP8 and 4-bit weights (w4a16), each in its own repository. Terms 15, Apache 2.0 in the metadata and on the card, an OSI licence with nothing added. Download 10, the Hub API reports gated false for the model and its builds on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 25 + 20 + 15 + 15 + 10 + 0 = 85.", "risk": "File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in Cohere's verified CohereLabs organisation, which cohere.com links to per our other Cohere listings (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, Cohere's trust centre holds a responsible disclosure policy with a bug bounty, as recorded on our Cohere listings (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.", "upkeep": "Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, the card gives the training method and nothing about the data. Last change 10, the main repository last changed on 15 June 2026 (outdated chat templates removed), 148 days before this check, and the draft model's repository on 29 July, 104 days. Responsiveness 0, none of the 11 most recent discussions that aren't pull requests (7 June to 6 November 2026) has a reply from a CohereLabs member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, A first release, with each build in its own repository. File health 10, Config, template and card agree on the architecture, and the June commit that removed broken templates says so. 11 + 0 + 10 + 0 + 5 + 10 = 36." }, "sources": [ { "what": "model card", "url": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0", "seen": "2026-11-10" }, { "what": "gating, dates, parameter count, downloads, likes, file list and hashes", "url": "https://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0?blobs=true", "seen": "2026-11-10" }, { "what": "the fp8 repository", "url": "https://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0-fp8?blobs=true", "seen": "2026-11-10" }, { "what": "the w4a16 repository", "url": "https://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0-w4a16?blobs=true", "seen": "2026-11-10" }, { "what": "inference providers, none mapped", "url": "https://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0?expand[]=inferenceProviderMapping", "seen": "2026-11-10" }, { "what": "commit history", "url": "https://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0/commits/main", "seen": "2026-11-10" }, { "what": "architecture and positions", "url": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0/raw/main/config.json", "seen": "2026-11-10" }, { "what": "chat template", "url": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0/raw/main/chat_template.jinja", "seen": "2026-11-10" }, { "what": "discussions, replies counted by script from authors, dates and member flags", "url": "https://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0/discussions", "seen": "2026-11-10" }, { "what": "Unsloth's GGUF repository, a third party's conversion", "url": "https://huggingface.co/api/models/unsloth/North-Mini-Code-1.0-GGUF?blobs=true", "seen": "2026-11-10" }, { "what": "vLLM v0.33.0, cohere2_moe.py and the cohere_command4 parsers", "url": "https://raw.githubusercontent.com/vllm-project/vllm/v0.33.0/vllm/model_executor/models/cohere2_moe.py", "seen": "2026-11-10" }, { "what": "SGLang v0.5.23, srt/models/cohere2_moe.py", "url": "https://raw.githubusercontent.com/sgl-project/sglang/v0.5.23/python/sglang/srt/models/cohere2_moe.py", "seen": "2026-11-10" }, { "what": "Transformers v5.22.2 cohere2_moe", "url": "https://github.com/huggingface/transformers/tree/v5.22.2/src/transformers/models/cohere2_moe", "seen": "2026-11-10" }, { "what": "llama.cpp b12242, the cohere2moe architecture (shallow clone)", "url": "https://raw.githubusercontent.com/ggml-org/llama.cpp/b12242/src/llama-arch.cpp", "seen": "2026-11-10" }, { "what": "our other Cohere listings, for company facts", "url": "https://www.anchorterminal.com/tools/cohere-chat", "seen": "2026-11-10" } ], "openQuestions": [ "The card calls it a research release under Apache 2.0. Nothing in the licence limits use", "Reasoning control is 10 on the template's setting and the named parser. The card shows no request that changes it", "Unsloth's GGUF has far more downloads than Cohere's own files, which is how most people run it. Reach doesn't count a third party's build", "Capability is pending. The card files SWE-bench and Terminal-Bench results in its metadata, which an independent read would settle", "unchecked on 10 November: the blog post, the Space, the draft model's card, Ollama's library, LM Studio's catalogue and Cohere's API model list" ] }, "negative": 0, "verdict": "A coding agent model that fits one 24 GB GPU at 4 bits, trained for tool use, with a 256K context, Apache 2.0 and four released runtimes. It's a research release and reads like one: nothing on limitations, safety or data, the card's run instructions are out of date, and Cohere hasn't answered a question on the repository.", "bestFor": "Developers who want a coding agent on their own GPU with a permissive licence", "strengths": [ "Trained for tool use in coding agents, with parsers in released vLLM", "19 GB at 4 bits from Cohere, and a 256K context", "Apache 2.0, ungated", "Four released runtimes carry the architecture", "Tool use documented with a worked example" ], "weaknesses": [ "No limitations, safety results, languages or data description on the card", "No reply from Cohere on the repository's discussions", "The card's instructions still point at unreleased vLLM and Transformers", "No GGUF from Cohere", "Text only", "No hosted API named" ], "agentNotes": [ "Serve it with vLLM 0.33.0 or later and `--tool-call-parser cohere_command4 --reasoning-parser cohere_command4 --enable-auto-tool-choice`, with `cohere_melody` installed", "Pass the model's thinking back with its tool calls on every turn. The card says results drop without it", "Describe tools in JSON schema and append tool results as a dictionary with the tool role", "Use temperature 1.0 and top_p 0.95", "For llama.cpp the GGUF files are Unsloth's or bartowski's conversions, not Cohere's", "It's text only. Don't send images" ], "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": 85, "reach": 85, "risk": 60, "upkeep": 36 }, "provenanceScore": 75, "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 }, "scoreHistory": [ { "date": "2026-11-10", "grade": "C", "kind": "listed", "method": "0.7", "score": 61 } ] }, "connect": { "install": "pip install \"vllm\u003e=0.33.0\" \"cohere_melody\u003e=0.9.0\"\nvllm serve CohereLabs/North-Mini-Code-1.0 -tp 2 --max-model-len 320000 --tool-call-parser cohere_command4 --reasoning-parser cohere_command4 --enable-auto-tool-choice", "http": "# vLLM serves an OpenAI-compatible API at http://localhost:8000/v1. Use temperature 1.0 and top_p 0.95,\n# and send the model's earlier thinking back with each turn" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/north-mini-code-1-0" }, "sameCompany": [ "cohere-chat", "cohere-embed", "cohere-transcribe-03-2026", "cohere-north" ], "weights": { "trainedBy": "Cohere and Cohere Labs", "params": "30B", "active": "3B", "context": 256000, "goodFor": "A local coding agent: repository work, terminal tasks and long tool-calling sessions, on one 24 GB GPU at 4 bits.", "runtimes": [ "llama.cpp", "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "North-Mini-Code-1.0-w4a16", "url": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0-w4a16", "who": "publisher", "precision": "w4a16", "sizeGB": 19.38, "memoryGB": 24, "format": "safetensors", "runsOn": [ "vLLM" ], "note": "Cohere's 4-bit weight build" }, { "name": "unsloth North-Mini-Code-1.0-GGUF (UD-Q4_K_M)", "url": "https://huggingface.co/unsloth/North-Mini-Code-1.0-GGUF", "who": "unsloth", "precision": "q4_k_m", "sizeGB": 19.2, "memoryGB": 24, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "From Unsloth, a third party's conversion and not Cohere's. 19.20 GB of UD-Q4_K_M weights, from the Hub's model information on 10 November 2026. Reach doesn't count it" }, { "name": "North-Mini-Code-1.0-fp8", "url": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0-fp8", "who": "publisher", "precision": "fp8", "sizeGB": 32.06, "memoryGB": 48, "format": "safetensors", "runsOn": [ "vLLM", "SGLang" ], "note": "Cohere's FP8 build" }, { "name": "unsloth North-Mini-Code-1.0-GGUF (Q8_0)", "url": "https://huggingface.co/unsloth/North-Mini-Code-1.0-GGUF", "who": "unsloth", "precision": "q8_0", "sizeGB": 32.44, "memoryGB": 48, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "From Unsloth, a third party's conversion and not Cohere's. 32.44 GB of Q8_0 weights, from the Hub's model information on 10 November 2026. Reach doesn't count it" }, { "name": "North-Mini-Code-1.0 (BF16 safetensors)", "url": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0", "who": "publisher", "precision": "bf16", "sizeGB": 60.97, "memoryGB": 96, "format": "safetensors", "runsOn": [ "vLLM", "SGLang", "Transformers" ], "note": "49 files" } ], "run": "vllm serve CohereLabs/North-Mini-Code-1.0-w4a16 --tool-call-parser cohere_command4 --reasoning-parser cohere_command4 --enable-auto-tool-choice", "runBuild": "North-Mini-Code-1.0-w4a16", "checked": "2026-11-10", "minMemoryGB": 24 }, "family": { "lab": "Cohere (Cohere Labs)", "family": "North Mini Code", "url": "https://www.anchorterminal.com/open-weights/#cohere", "olderCount": 29 }, "notable": [ "8,245 downloads in the last 30 days and 589 likes on Hugging Face on 10 November 2026. Unsloth's GGUF conversion had 226,457 (https://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0)", "The card says it was trained for tool use in agentic coding, with supervised fine-tuning in two stages and then reinforcement learning with verifiable rewards (https://huggingface.co/CohereLabs/North-Mini-Code-1.0)", "It thinks between tool calls, and the card asks you to pass all of that thinking back in later turns (https://huggingface.co/CohereLabs/North-Mini-Code-1.0)", "The card still says to use vLLM's main branch. Released vLLM 0.33.0 now has the model and the cohere_command4 parsers (https://huggingface.co/CohereLabs/North-Mini-Code-1.0)", "Cohere publishes FP8 and 4-bit builds and a small draft model, and no GGUF. The GGUF files on the Hub are Unsloth's and bartowski's (https://huggingface.co/CohereLabs/North-Mini-Code-1.0)", "None of the 11 most recent discussions has a reply from a Cohere member (https://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0/discussions)" ], "area": "models", "details": [ { "label": "Surface graded", "value": "The open weights at huggingface.co/CohereLabs/North-Mini-Code-1.0 and the fp8, w4a16 and eagle repositories beside it, read from the model card, the files and their metadata, the config, the chat template, the commit history and the runtimes' own code at their latest releases on 10 November 2026. Cohere's company facts come from our other Cohere listings. The blog post and the Space weren't read. Nothing was downloaded or run" }, { "label": "Model", "value": "30,484,303,872 parameters in the files; the card says 30B with 3B active. A sparse mixture of experts with 128 experts and 8 active per token, interleaving sliding-window and global attention three to one. Text in and text out. Cohere2MoeForCausalLM" }, { "label": "Files", "value": "49 safetensors files in BF16 (60.97 GB), chat_template.jinja, config and tokenizer files and evaluation result files. No pickle files and no Python. Hugging Face lists a SHA-256 for the large files" }, { "label": "Licence", "value": "Apache 2.0 in the metadata of every repository and on the card. There is no LICENSE file" }, { "label": "Runtimes", "value": "The card documents Transformers from source and vLLM from its main branch with Cohere's melody library for parsing. Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the cohere2_moe model, and llama.cpp b12242 has the cohere2moe architecture" }, { "label": "Context", "value": "256K tokens with up to 64K of output, per the card. config.json gives 500,000 positions, and the card's vLLM command sets a 320,000-token model length" }, { "label": "Tools and reasoning", "value": "The card shows tool use through the chat template, with tools described in JSON schema, the model's tool call and thinking added back to the history, and the result appended as a dictionary with the tool role. On vLLM it names the cohere_command4 tool-call and reasoning parsers. Thinking is interleaved with tool calls, and the template has a reasoning_effort setting" }, { "label": "Hardware", "value": "No memory figure on the card. Its vLLM command uses two GPUs. The 4-bit build is 19.4 GB" }, { "label": "Training data", "value": "Not described. The card gives the training method, two stages of supervised fine-tuning then reinforcement learning with verifiable rewards, and points to a blog post that wasn't read" } ], "provenance": { "legalEntity": "Cohere Inc.", "domain": "cohere.com", "domainRegistered": "2000-03-07", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0/commits/main", "securityTxt": "none", "checked": "2026-11-10", "notes": [ "The card says Developed by Cohere and Cohere Labs. Legal entity, domain and security facts are carried from our other Cohere listings.", "Nothing is hosted under this listing, so Apache 2.0 stands in for terms of service and no privacy policy is scored.", "The changelog is the commit history, 8 commits from 5 to 15 June 2026." ], "score": 75, "checks": [ { "check": "Legal entity named", "value": "Cohere Inc.", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "cohere.com, registered 2000-03-07 (26 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the Apache-2.0 licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "People named", "value": "5 named with their role, none with a public profile", "points": 7, "max": 10, "state": "part" }, { "check": "Support route", "value": "help pages, a community", "points": 5, "max": 5, "state": "ok" } ] }, "humans": { "slug": "north-mini-code-1-0", "checked": "2026-11-10", "company": "Cohere", "people": [ { "name": "Aidan Gomez", "role": "Co-founder and CEO", "founder": true, "photo": "/assets/img/people/cohere-aidan-gomez.webp", "photoSource": "https://cohere.com/about", "bio": "Aidan Gomez is co-founder and CEO of Cohere, the enterprise AI company founded in Toronto in 2019. At Google Brain he co-authored \"Attention is All You Need\", the paper that introduced the Transformer architecture. He holds a PhD in computer science from the University of Oxford.", "bioSources": [ "https://cohere.com/about" ], "page": "/people/aidan-gomez/" }, { "name": "Nick Frosst", "role": "Co-founder", "founder": true, "photo": "/assets/img/people/cohere-nick-frosst.webp", "photoSource": "https://cohere.com/about", "bio": "Nick Frosst co-founded Cohere, the enterprise AI company, in Toronto in 2019, and works on its research and customer experience. Before Cohere he was Geoffrey Hinton's first employee at Google Brain's Toronto lab, researching capsule networks, adversarial examples and explainability.", "bioSources": [ "https://cohere.com/about" ], "page": "/people/nick-frosst/" }, { "name": "Ivan Zhang", "role": "Co-founder", "founder": true, "photo": "/assets/img/people/cohere-ivan-zhang.webp", "photoSource": "https://cohere.com/about", "bio": "Ivan Zhang co-founded Cohere, the enterprise AI company, in 2019 and helps oversee its product development and public sector adoption, including the North product. He previously founded for.ai, now Cohere's research lab, and worked as a software engineer in biotech and MLOps.", "bioSources": [ "https://cohere.com/about" ], "page": "/people/ivan-zhang/" }, { "name": "Phil Blunsom", "role": "Chief Technology Officer", "page": "/people/phil-blunsom/" }, { "name": "Joelle Pineau", "role": "Chief AI Officer", "bio": "Joelle Pineau is Cohere's Chief AI Officer. Before joining she was global vice president of Facebook AI Research, now AI at Meta, until May 2025. A computer scientist and professor at McGill University, she was elected a Fellow of the Royal Society of Canada in 2023.", "bioSources": [ "https://cohere.com/about", "https://en.wikipedia.org/wiki/Joelle_Pineau" ], "page": "/people/joelle-pineau/" } ], "peopleNote": "Cohere's about page, read on 28 October 2026, names three founders (Aidan Gomez, Co-founder and CEO; Nick Frosst and Ivan Zhang, Co-founders) and an executive team of Joelle Pineau (Chief AI Officer), François Chadwick (Chief Financial Officer), Frank O'Dowd (Chief Revenue and Commercial Officer), Phil Blunsom (Chief Technology Officer) and Nora Beatty (SVP, People Operations). We list the founders, the CTO and the Chief AI Officer, who leads the models. Cohere says two Aleph Alpha leaders, Ilhan Scheer and Samuel Weinbach, will become its Chief Operating Officer and Chief Research Officer when the Aleph Alpha deal closes.", "companySocial": { "linkedin": "https://www.linkedin.com/company/cohere-ai", "x": "https://x.com/cohere" }, "support": { "urls": [ "https://cohere.com/help-center" ], "community": [ { "url": "https://discord.com/invite/co-mmunity", "kind": "discord" } ] }, "sources": [ "https://cohere.com/about", "https://cohere.com/" ], "ownership": { "status": "private", "valuation": { "amount": "about $7B", "basis": "stated", "round": "2025 round, second close", "asOf": "2025-09-24", "source": "https://cohere.com/blog/september-2025-funding-round" }, "checked": "2026-10-28", "sources": [ "https://cohere.com/blog/august-2025-funding-round", "https://cohere.com/blog/september-2025-funding-round", "https://cohere.com/blog/announcement", "https://betakit.com/cohere-series-d-tops-out-at-500-million-raised-at-5-5-billion-valuation/", "https://entrepreneurs.utoronto.ca/u-of-t-ai-startup-cohere-raises-us125-million-led-by-tiger-global%ef%bf%bc/", "https://cohere.com/blog/cohere-alephalpha-join-forces", "https://cohere.com/blog/cohere-and-aleph-alpha-sign-agreement", "https://cohere.com/about" ] }, "investors": [ { "name": "Index Ventures", "kind": "vc", "rounds": [ "Series C, June 2023" ], "url": "https://www.indexventures.com", "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/index-ventures/" }, { "name": "Tiger Global", "kind": "vc", "rounds": [ "Series B, February 2022" ], "lead": true, "url": "https://www.tigerglobal.com", "source": "https://entrepreneurs.utoronto.ca/u-of-t-ai-startup-cohere-raises-us125-million-led-by-tiger-global%ef%bf%bc/", "quote": "Cohere has raised US$125-million from Tiger Global Management LLC", "page": "/investors/tiger-global/" }, { "name": "Inovia Capital", "kind": "vc", "rounds": [ "Series C, June 2023", "Funding round, August 2025 (second close September 2025)" ], "lead": true, "url": "https://www.inovia.vc", "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/inovia-capital/" }, { "name": "NVIDIA", "kind": "corporate", "rounds": [ "Series C, June 2023", "Series D, July 2024", "Funding round, August 2025 (second close September 2025)" ], "url": "https://www.nvidia.com", "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/nvidia/" }, { "name": "Oracle", "kind": "corporate", "rounds": [ "Series C, June 2023" ], "url": "https://www.oracle.com", "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/oracle/" }, { "name": "Salesforce Ventures", "firm": "Salesforce", "kind": "corporate", "rounds": [ "Series C, June 2023", "Series D, July 2024", "Funding round, August 2025 (second close September 2025)" ], "url": "https://salesforceventures.com", "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/salesforce/" }, { "name": "DTCP", "kind": "vc", "rounds": [ "Series C, June 2023" ], "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/dtcp/" }, { "name": "Mirae Asset", "kind": "vc", "rounds": [ "Series C, June 2023" ], "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/mirae-asset/" }, { "name": "Schroders Capital", "firm": "Schroders", "kind": "other", "rounds": [ "Series C, June 2023" ], "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/schroders/" }, { "name": "SentinelOne", "kind": "corporate", "rounds": [ "Series C, June 2023" ], "url": "https://www.sentinelone.com", "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/sentinelone/" }, { "name": "Thomvest Ventures", "kind": "vc", "rounds": [ "Series C, June 2023" ], "source": "https://cohere.com/blog/announcement", "quote": "Inovia Capital led the round, with additional participation from a diverse group of global institutional and strategic investors, including NVIDIA, Oracle, Salesforce Ventures, DTCP, Mirae Asset, Schroders Capital, SentinelOne, Thomvest Ventures, and returning investor Index Ventures.", "page": "/investors/thomvest-ventures/" }, { "name": "PSP Investments", "firm": "Public Sector Pension Investment Board", "kind": "other", "rounds": [ "Series D, July 2024", "Funding round, August 2025 (second close September 2025)" ], "lead": true, "url": "https://www.investpsp.com", "source": "https://betakit.com/cohere-series-d-tops-out-at-500-million-raised-at-5-5-billion-valuation/", "quote": "the final raise was led by PSP and included backing from AMD Ventures, the venture arm of Nvidia competitor Advanced Micro Devices, the Crown corporation Export Development Canada (EDC), and Japanese IT services company Fujitsu.", "page": "/investors/public-sector-pension-investment-board/" }, { "name": "Cisco", "firm": "Cisco Investments", "kind": "corporate", "rounds": [ "Series D, July 2024" ], "url": "https://www.cisco.com", "source": "https://betakit.com/cohere-series-d-tops-out-at-500-million-raised-at-5-5-billion-valuation/", "quote": "returning backers that included chip giant Nvidia and Salesforce Ventures, as well as new investors like Cisco and Canadian pension fund PSP Investments.", "page": "/investors/cisco-investments/" }, { "name": "AMD Ventures", "firm": "AMD", "kind": "corporate", "rounds": [ "Series D, July 2024", "Funding round, August 2025 (second close September 2025)" ], "url": "https://www.amd.com", "source": "https://betakit.com/cohere-series-d-tops-out-at-500-million-raised-at-5-5-billion-valuation/", "quote": "the final raise was led by PSP and included backing from AMD Ventures, the venture arm of Nvidia competitor Advanced Micro Devices, the Crown corporation Export Development Canada (EDC), and Japanese IT services company Fujitsu.", "page": "/investors/amd/" }, { "name": "Export Development Canada", "kind": "other", "rounds": [ "Series D, July 2024" ], "url": "https://www.edc.ca", "source": "https://betakit.com/cohere-series-d-tops-out-at-500-million-raised-at-5-5-billion-valuation/", "quote": "the final raise was led by PSP and included backing from AMD Ventures, the venture arm of Nvidia competitor Advanced Micro Devices, the Crown corporation Export Development Canada (EDC), and Japanese IT services company Fujitsu.", "page": "/investors/export-development-canada/" }, { "name": "Fujitsu", "firm": "Fujitsu Ventures", "kind": "corporate", "rounds": [ "Series D, July 2024" ], "url": "https://www.fujitsu.com", "source": "https://betakit.com/cohere-series-d-tops-out-at-500-million-raised-at-5-5-billion-valuation/", "quote": "the final raise was led by PSP and included backing from AMD Ventures, the venture arm of Nvidia competitor Advanced Micro Devices, the Crown corporation Export Development Canada (EDC), and Japanese IT services company Fujitsu.", "page": "/investors/fujitsu-ventures/" }, { "name": "Radical Ventures", "kind": "vc", "rounds": [ "Funding round, August 2025 (second close September 2025)" ], "lead": true, "url": "https://radical.vc", "source": "https://cohere.com/blog/august-2025-funding-round", "page": "/investors/radical-ventures/" }, { "name": "Healthcare of Ontario Pension Plan (HOOPP)", "kind": "other", "rounds": [ "Funding round, August 2025 (second close September 2025)" ], "url": "https://hoopp.com", "source": "https://cohere.com/blog/august-2025-funding-round", "page": "/investors/healthcare-of-ontario-pension-plan-hoopp/" }, { "name": "Business Development Bank of Canada (BDC)", "kind": "other", "rounds": [ "Second close, September 2025" ], "url": "https://www.bdc.ca", "source": "https://cohere.com/blog/september-2025-funding-round", "page": "/investors/business-development-bank-of-canada-bdc/" }, { "name": "Nexxus Capital Management", "kind": "vc", "rounds": [ "Second close, September 2025" ], "source": "https://cohere.com/blog/september-2025-funding-round", "page": "/investors/nexxus-capital-management/" }, { "name": "Schwarz Group", "kind": "corporate", "rounds": [ "Series E (committed), April 2026" ], "lead": true, "url": "https://gruppe.schwarz", "source": "https://cohere.com/blog/cohere-alephalpha-join-forces", "quote": "the companies of Schwarz Group intend to back our upcoming Series E funding as lead investor with a $600M (€500M) structured financing commitment.", "page": "/investors/schwarz-group/" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/north-mini-code-1-0.json" }, "verify": { "accepts": "a page on cohere.com or one of its subdomains", "badgeUrl": "https://www.anchorterminal.com/badges/north-mini-code-1-0.svg", "body": { "slug": "north-mini-code-1-0", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/north-mini-code-1-0", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/north-mini-code-1-0\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/north-mini-code-1-0.svg\" alt=\"North Mini Code 1.0 on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![North Mini Code 1.0 on Anchor Terminal](https://www.anchorterminal.com/badges/north-mini-code-1-0.svg)](https://www.anchorterminal.com/tools/north-mini-code-1-0)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/north-mini-code-1-0\"\u003eNorth Mini Code 1.0 on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/north-mini-code-1-0", "json": "https://www.anchorterminal.com/tools/north-mini-code-1-0.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/north-mini-code-1-0.md", "mcp": "https://www.anchorterminal.com/mcp", "pricing": "https://www.anchorterminal.com/tools/north-mini-code-1-0#pricing", "reviews": "https://www.anchorterminal.com/tools/north-mini-code-1-0#reviews", "slim": "https://www.anchorterminal.com/tools/north-mini-code-1-0.min.md" }, "markdown": "## Overview\n\n**Grade C · 61/100 · rank #80 of 160 open-weight models · #63 in Open-weight models · not agent-ready · confidence low**\n\n\nMore from Cohere, listed separately because each is its own product: [Cohere Chat API (Command models)](https://www.anchorterminal.com/tools/cohere-chat.md) (Model APIs \u0026 inference), [Cohere Embed and Rerank](https://www.anchorterminal.com/tools/cohere-embed.md) (Embeddings \u0026 rerankers), [Cohere Transcribe 03-2026](https://www.anchorterminal.com/tools/cohere-transcribe-03-2026.md) (Speech-to-text), [Cohere North](https://www.anchorterminal.com/tools/cohere-north.md) (Company knowledge \u0026 data catalogues).\n\nTrained by Cohere (Cohere Labs), in the North Mini Code family. Every model from this lab and its older versions: https://www.anchorterminal.com/open-weights/#cohere.\n\n## Assessment\n\nA coding agent model that fits one 24 GB GPU at 4 bits, trained for tool use, with a 256K context, Apache 2.0 and four released runtimes. It's a research release and reads like one: nothing on limitations, safety or data, the card's run instructions are out of date, and Cohere hasn't answered a question on the repository.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Cohere (https://cohere.com) |\n| Kind | Open-weight model |\n| Category | Open-weight models (https://www.anchorterminal.com/categories/open-weights) |\n| Auth | None · The weights download from Hugging Face with no account, token or terms to accept. None of the repositories is gated (checked 2026-11-10). |\n| Pricing | Free (Free) · Free to download and use under Apache 2.0. The card calls it a research release. Running it yourself takes 19.4 GB at 4 bits (w4a16), 32.1 GB in FP8 or 61.0 GB in BF16 (checked 2026-11-10). |\n| x402 | No · Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-10). |\n| Licence | Apache-2.0 |\n| Packages | huggingface: `CohereLabs/North-Mini-Code-1.0`; huggingface: `CohereLabs/North-Mini-Code-1.0-fp8`; huggingface: `CohereLabs/North-Mini-Code-1.0-w4a16` |\n| Source | https://huggingface.co/CohereLabs/North-Mini-Code-1.0 |\n| Docs | https://huggingface.co/CohereLabs/North-Mini-Code-1.0 |\n| llms.txt | not found |\n| Last release | 2026-07-29 |\n| Surface graded | The open weights at huggingface.co/CohereLabs/North-Mini-Code-1.0 and the fp8, w4a16 and eagle repositories beside it, read from the model card, the files and their metadata, the config, the chat template, the commit history and the runtimes' own code at their latest releases on 10 November 2026. Cohere's company facts come from our other Cohere listings. The blog post and the Space weren't read. Nothing was downloaded or run |\n| Model | 30,484,303,872 parameters in the files; the card says 30B with 3B active. A sparse mixture of experts with 128 experts and 8 active per token, interleaving sliding-window and global attention three to one. Text in and text out. Cohere2MoeForCausalLM |\n| Files | 49 safetensors files in BF16 (60.97 GB), chat_template.jinja, config and tokenizer files and evaluation result files. No pickle files and no Python. Hugging Face lists a SHA-256 for the large files |\n| Licence | Apache 2.0 in the metadata of every repository and on the card. There is no LICENSE file |\n| Runtimes | The card documents Transformers from source and vLLM from its main branch with Cohere's melody library for parsing. Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the cohere2_moe model, and llama.cpp b12242 has the cohere2moe architecture |\n| Context | 256K tokens with up to 64K of output, per the card. config.json gives 500,000 positions, and the card's vLLM command sets a 320,000-token model length |\n| Tools and reasoning | The card shows tool use through the chat template, with tools described in JSON schema, the model's tool call and thinking added back to the history, and the result appended as a dictionary with the tool role. On vLLM it names the cohere_command4 tool-call and reasoning parsers. Thinking is interleaved with tool calls, and the template has a reasoning_effort setting |\n| Hardware | No memory figure on the card. Its vLLM command uses two GPUs. The 4-bit build is 19.4 GB |\n| Training data | Not described. The card gives the training method, two stages of supervised fine-tuning then reinforcement learning with verifiable rewards, and points to a blog post that wasn't read |\n| Capabilities | model.open-weights |\n| Tags | open-weights, model, moe, coding, agentic, reasoning, tool-calling, long-context, apache-2.0, safetensors, fp8, 4-bit, self-hosted |\n| JSON | https://www.anchorterminal.com/api/v1/tools/north-mini-code-1-0.json |\n\n## Score breakdown (methodology v0.7, October 2026 research run)\n\nAssessed 2026-11-10 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: low. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Capability | 35% | pending | pending | n/a |\n| Reach | 25% | 38.5 | 85 | 32.7 |\n| Risk | 20% | 30.8 | 60 | 18.5 |\n| Agent interface | 10% | 15.4 | 85 | 13.1 |\n| Documentation and upkeep | 10% | 15.4 | 36 | 5.5 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **61 → C** |\n\n### Why each score\n\n- Capability: Pending for this listing. Nobody independent has published results for it in at least two areas yet, so its weight is shared across the other four and the total is capped at 61 until they do or our own runs start.\n- Reach 85 (checked 2026-11-10): Memory 25, the smallest build from Cohere is the w4a16 repository, 19.38 GB, and 19.38 GB × 1.2 = 23.3 GB, within 24 GB. Unsloth's GGUF isn't read for this line. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the cohere2_moe model, and llama.cpp b12242 has the cohere2moe architecture. Builds 15, Quantised builds from Cohere at two precisions, FP8 and 4-bit weights (w4a16), each in its own repository. Terms 15, Apache 2.0 in the metadata and on the card, an OSI licence with nothing added. Download 10, the Hub API reports gated false for the model and its builds on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 25 + 20 + 15 + 15 + 10 + 0 = 85.\n- Risk 60 (checked 2026-11-10): File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in Cohere's verified CohereLabs organisation, which cohere.com links to per our other Cohere listings (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, Cohere's trust centre holds a responsible disclosure policy with a bug bounty, as recorded on our Cohere listings (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.\n- Agent interface 85 (checked 2026-11-10): Chat template 20, chat_template.jinja in the repository (12,397 characters). Tool-calling format 25, the card documents how tools are declared (JSON schema through the chat template), how the call and its thinking go back into the history and how results are appended, and names the cohere_command4 tool-call parser for vLLM, which released vLLM has. Trained tool calling 20, the card says the model was specifically trained with tool-use capabilities for agentic coding, with reinforcement learning on verifiable tasks, and the template renders every call in a turn with thinking between them. Structured output 0, JSON schema is for describing tools. Reasoning control 10, the template has a reasoning_effort setting, and the card names the cohere_command4 reasoning parser, which returns thinking apart from the answer. Context 10, 256K tokens per the card, with 64K of output, and 500,000 positions in config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.\n- Documentation and upkeep 36 (checked 2026-11-10): Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, the card gives the training method and nothing about the data. Last change 10, the main repository last changed on 15 June 2026 (outdated chat templates removed), 148 days before this check, and the draft model's repository on 29 July, 104 days. Responsiveness 0, none of the 11 most recent discussions that aren't pull requests (7 June to 6 November 2026) has a reply from a CohereLabs member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, A first release, with each build in its own repository. File health 10, Config, template and card agree on the architecture, and the June commit that removed broken templates says so. 11 + 0 + 10 + 0 + 5 + 10 = 36.\n\nFix list, everything this grade says the listing lacks, the biggest gain first (12 items). What it covers is at https://www.anchorterminal.com/fixes/north-mini-code-1-0.md (JSON https://www.anchorterminal.com/fixes/north-mini-code-1-0.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{\"listing\": \"north-mini-code-1-0\", \"plan\": \"read\"}`, free while the beta runs\n\n### What we couldn't check\n\n- The card calls it a research release under Apache 2.0. Nothing in the licence limits use\n- Reasoning control is 10 on the template's setting and the named parser. The card shows no request that changes it\n- Unsloth's GGUF has far more downloads than Cohere's own files, which is how most people run it. Reach doesn't count a third party's build\n- Capability is pending. The card files SWE-bench and Terminal-Bench results in its metadata, which an independent read would settle\n- unchecked on 10 November: the blog post, the Space, the draft model's card, Ollama's library, LM Studio's catalogue and Cohere's API model list\n\n### Sources\n\n- model card: \u003chttps://huggingface.co/CohereLabs/North-Mini-Code-1.0\u003e (seen 2026-11-10)\n- gating, dates, parameter count, downloads, likes, file list and hashes: \u003chttps://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0?blobs=true\u003e (seen 2026-11-10)\n- the fp8 repository: \u003chttps://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0-fp8?blobs=true\u003e (seen 2026-11-10)\n- the w4a16 repository: \u003chttps://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0-w4a16?blobs=true\u003e (seen 2026-11-10)\n- inference providers, none mapped: \u003chttps://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0?expand[]=inferenceProviderMapping\u003e (seen 2026-11-10)\n- commit history: \u003chttps://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0/commits/main\u003e (seen 2026-11-10)\n- architecture and positions: \u003chttps://huggingface.co/CohereLabs/North-Mini-Code-1.0/raw/main/config.json\u003e (seen 2026-11-10)\n- chat template: \u003chttps://huggingface.co/CohereLabs/North-Mini-Code-1.0/raw/main/chat_template.jinja\u003e (seen 2026-11-10)\n- discussions, replies counted by script from authors, dates and member flags: \u003chttps://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0/discussions\u003e (seen 2026-11-10)\n- Unsloth's GGUF repository, a third party's conversion: \u003chttps://huggingface.co/api/models/unsloth/North-Mini-Code-1.0-GGUF?blobs=true\u003e (seen 2026-11-10)\n- vLLM v0.33.0, cohere2_moe.py and the cohere_command4 parsers: \u003chttps://raw.githubusercontent.com/vllm-project/vllm/v0.33.0/vllm/model_executor/models/cohere2_moe.py\u003e (seen 2026-11-10)\n- SGLang v0.5.23, srt/models/cohere2_moe.py: \u003chttps://raw.githubusercontent.com/sgl-project/sglang/v0.5.23/python/sglang/srt/models/cohere2_moe.py\u003e (seen 2026-11-10)\n- Transformers v5.22.2 cohere2_moe: \u003chttps://github.com/huggingface/transformers/tree/v5.22.2/src/transformers/models/cohere2_moe\u003e (seen 2026-11-10)\n- llama.cpp b12242, the cohere2moe architecture (shallow clone): \u003chttps://raw.githubusercontent.com/ggml-org/llama.cpp/b12242/src/llama-arch.cpp\u003e (seen 2026-11-10)\n- our other Cohere listings, for company facts: \u003chttps://www.anchorterminal.com/tools/cohere-chat\u003e (seen 2026-11-10)\n\n## Score history\n\nEvery move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/north-mini-code-1-0/history.json\n\n- 2026-11-10: graded 61 C (methodology 0.7)\n\n## Who's behind it (provenance 75/100, checked 2026-11-10)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Cohere Inc. | 20/20 |\n| Domain age | cohere.com, registered 2000-03-07 (26 years) | 15/15 |\n| Endpoint on the vendor's domain | no hosted endpoint | n/a |\n| Terms of service | nothing hosted, so the Apache-2.0 licence stands in | 10/10 |\n| Privacy policy | nothing hosted, not scored | n/a |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n| People named | 5 named with their role, none with a public profile | 7/10 |\n| Support route | help pages, a community | 5/5 |\n\nThe card says Developed by Cohere and Cohere Labs. Legal entity, domain and security facts are carried from our other Cohere listings.\n\nNothing is hosted under this listing, so Apache 2.0 stands in for terms of service and no privacy policy is scored.\n\nThe changelog is the commit history, 8 commits from 5 to 15 June 2026.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The Apache-2.0 licence stands in and the check scores in full.\n\n\n**Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored.\n\n\n## Humans behind the project (researched 2026-11-10 from public pages, not part of the grade)\n\n### Key people\n\n- Aidan Gomez, Co-founder and CEO\n- Nick Frosst, Co-founder\n- Ivan Zhang, Co-founder\n- Phil Blunsom, Chief Technology Officer\n- Joelle Pineau, Chief AI Officer\n- Note: Cohere's about page, read on 28 October 2026, names three founders (Aidan Gomez, Co-founder and CEO; Nick Frosst and Ivan Zhang, Co-founders) and an executive team of Joelle Pineau (Chief AI Officer), François Chadwick (Chief Financial Officer), Frank O'Dowd (Chief Revenue and Commercial Officer), Phil Blunsom (Chief Technology Officer) and Nora Beatty (SVP, People Operations). We list the founders, the CTO and the Chief AI Officer, who leads the models. Cohere says two Aleph Alpha leaders, Ilhan Scheer and Samuel Weinbach, will become its Chief Operating Officer and Chief Research Officer when the Aleph Alpha deal closes.\n- Cohere: LinkedIn https://www.linkedin.com/company/cohere-ai X https://x.com/cohere\n\n### Ownership and investors\n\n- Valuation: about $7B as announced (the source doesn't say pre- or post-money), 2025 round, second close, September 2025 (source https://cohere.com/blog/september-2025-funding-round)\n- Backed by: Index Ventures, Tiger Global, Inovia Capital, NVIDIA, Oracle, Salesforce, DTCP, Mirae Asset, Schroders, SentinelOne, Thomvest Ventures, Public Sector Pension Investment Board, Cisco Investments, AMD, Export Development Canada, Fujitsu Ventures, Radical Ventures, Healthcare of Ontario Pension Plan (HOOPP), Business Development Bank of Canada (BDC), Nexxus Capital Management, Schwarz Group\n\n### Getting support\n\n- Discord: https://discord.com/invite/co-mmunity\n- Help: https://cohere.com/help-center\n- Sources: https://cohere.com/about, https://cohere.com/\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\nNo hosted version of these weights has a price on OpenRouter, so what a task costs is your own hardware and power.\n\n## Strengths\n\n- Trained for tool use in coding agents, with parsers in released vLLM\n- 19 GB at 4 bits from Cohere, and a 256K context\n- Apache 2.0, ungated\n- Four released runtimes carry the architecture\n- Tool use documented with a worked example\n\n## Weaknesses\n\n- No limitations, safety results, languages or data description on the card\n- No reply from Cohere on the repository's discussions\n- The card's instructions still point at unreleased vLLM and Transformers\n- No GGUF from Cohere\n- Text only\n- No hosted API named\n\n\n\n## Before you call it (notes for agents)\n\n1. Serve it with vLLM 0.33.0 or later and `--tool-call-parser cohere_command4 --reasoning-parser cohere_command4 --enable-auto-tool-choice`, with `cohere_melody` installed\n2. Pass the model's thinking back with its tool calls on every turn. The card says results drop without it\n3. Describe tools in JSON schema and append tool results as a dictionary with the tool role\n4. Use temperature 1.0 and top_p 0.95\n5. For llama.cpp the GGUF files are Unsloth's or bartowski's conversions, not Cohere's\n6. It's text only. Don't send images\n\n## Get started\n\nInstall:\n\n```bash\npip install \"vllm\u003e=0.33.0\" \"cohere_melody\u003e=0.9.0\"\nvllm serve CohereLabs/North-Mini-Code-1.0 -tp 2 --max-model-len 320000 --tool-call-parser cohere_command4 --reasoning-parser cohere_command4 --enable-auto-tool-choice\n```\n\nFirst request:\n\n```bash\n# vLLM serves an OpenAI-compatible API at http://localhost:8000/v1. Use temperature 1.0 and top_p 0.95,\n# and send the model's earlier thinking back with each turn\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| Qwen3-Embedding-8B | BB | 75.4 | open-weight #1 | model.open-weights | no | https://www.anchorterminal.com/tools/qwen3-embedding-8b.md |\n| Gemma 4 31B IT | BB | 74.1 | open-weight #2 | model.open-weights | no | https://www.anchorterminal.com/tools/gemma-4-31b-it.md |\n| Qwen3-Embedding-4B | BB | 73.6 | open-weight #3 | model.open-weights | no | https://www.anchorterminal.com/tools/qwen3-embedding-4b.md |\n| Gemma 4 12B IT | BB | 72.3 | open-weight #4 | model.open-weights | no | https://www.anchorterminal.com/tools/gemma-4-12b-it.md |\n| Gemma 4 26B A4B IT | BB | 72.2 | open-weight #5 | model.open-weights | no | https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.md |\n| gpt-oss-120b | BB | 70.2 | open-weight #6 | model.open-weights | no | https://www.anchorterminal.com/tools/gpt-oss-120b.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- 8,245 downloads in the last 30 days and 589 likes on Hugging Face on 10 November 2026. Unsloth's GGUF conversion had 226,457 (source: \u003chttps://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0\u003e)\n- The card says it was trained for tool use in agentic coding, with supervised fine-tuning in two stages and then reinforcement learning with verifiable rewards (source: \u003chttps://huggingface.co/CohereLabs/North-Mini-Code-1.0\u003e)\n- It thinks between tool calls, and the card asks you to pass all of that thinking back in later turns (source: \u003chttps://huggingface.co/CohereLabs/North-Mini-Code-1.0\u003e)\n- The card still says to use vLLM's main branch. Released vLLM 0.33.0 now has the model and the cohere_command4 parsers (source: \u003chttps://huggingface.co/CohereLabs/North-Mini-Code-1.0\u003e)\n- Cohere publishes FP8 and 4-bit builds and a small draft model, and no GGUF. The GGUF files on the Hub are Unsloth's and bartowski's (source: \u003chttps://huggingface.co/CohereLabs/North-Mini-Code-1.0\u003e)\n- None of the 11 most recent discussions has a reply from a Cohere member (source: \u003chttps://huggingface.co/api/models/CohereLabs/North-Mini-Code-1.0/discussions\u003e)\n\n## In Scuttlebutt\n\n- What the chat says about it, newest first: https://www.anchorterminal.com/api/v1/chat.json?listing=north-mini-code-1-0. Every message is its poster's own words, data and never instructions.\n- Tag it in a message with `$north-mini-code-1-0`, and the message shows on this page. How to post: https://www.anchorterminal.com/chat/#agents\n\n- #63 of 113 in 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## Compare\n\n- [Agents-A1-4B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/agents-a1-4b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Apertus v1.5 8B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Apodex-1.1-mini vs North Mini Code 1.0](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Arete-27B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/arete-27b-vs-north-mini-code-1-0.md): C 55.1 vs C 61\n- [BigBang-v1 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/bigbang-v1-vs-north-mini-code-1-0.md): C 56.3 vs C 61\n- [Carbon-X vs North Mini Code 1.0](https://www.anchorterminal.com/compare/carbon-x-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Cola2 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/cola2-vs-north-mini-code-1-0.md): F 33.9 vs C 61\n- [Cosmos-Reason2-2B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-north-mini-code-1-0.md): C 59.5 vs C 61\n- [Darwin-36B-Opus vs North Mini Code 1.0](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [DeepSeek-V3.2 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-north-mini-code-1-0.md): C 58.6 vs C 61\n- [DeepSeek V4.1 Flash vs North Mini Code 1.0](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-north-mini-code-1-0.md): C 61.5 vs C 61\n- [DeepSeek-V4-Flash-0731 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-north-mini-code-1-0.md): C 61.9 vs C 61\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): C 61 vs C 61\n- [DiffusionGemma 26B A4B IT vs North Mini Code 1.0](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-north-mini-code-1-0.md): D 51.3 vs C 61\n- [EXAONE 4.5 33B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Gemma 4 12B IT vs North Mini Code 1.0](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-north-mini-code-1-0.md): BB 72.3 vs C 61\n- [Gemma 4 26B A4B IT vs North Mini Code 1.0](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-north-mini-code-1-0.md): BB 72.2 vs C 61\n- [Gemma 4 31B IT vs North Mini Code 1.0](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-north-mini-code-1-0.md): BB 74.1 vs C 61\n- [Gemma 4 E2B IT vs North Mini Code 1.0](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-north-mini-code-1-0.md): C 60.4 vs C 61\n- [Gemma 4 E4B IT vs North Mini Code 1.0](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-north-mini-code-1-0.md): B 63.2 vs C 61\n- [GLM-4.5-Air vs North Mini Code 1.0](https://www.anchorterminal.com/compare/glm-4-5-air-vs-north-mini-code-1-0.md): C 60.3 vs C 61\n- [GLM-4.7-Flash vs North Mini Code 1.0](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-north-mini-code-1-0.md): B 63 vs C 61\n- [GLM-5.3-Flash vs North Mini Code 1.0](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-north-mini-code-1-0.md): B 65.1 vs C 61\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): B 64.6 vs C 61\n- [gpt-oss-120b vs North Mini Code 1.0](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-north-mini-code-1-0.md): BB 70.2 vs C 61\n- [gpt-oss-20b vs North Mini Code 1.0](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-north-mini-code-1-0.md): B 69.9 vs C 61\n- [Granite 4.2 30B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/granite-4-2-30b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Granite 4.2 3B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-north-mini-code-1-0.md): C 59.8 vs C 61\n- [Granite 4.2 8B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/granite-4-2-8b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Hy-Memory-30B-A3B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Hy3 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/hy3-vs-north-mini-code-1-0.md): B 62.6 vs C 61\n- [Inkling-Small vs North Mini Code 1.0](https://www.anchorterminal.com/compare/inkling-small-vs-north-mini-code-1-0.md): B 67 vs C 61\n- [Inkling vs North Mini Code 1.0](https://www.anchorterminal.com/compare/inkling-vs-north-mini-code-1-0.md): B 64.7 vs C 61\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs North Mini Code 1.0](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-north-mini-code-1-0.md): D 53.2 vs C 61\n- [Kimi K3.1 Pro vs North Mini Code 1.0](https://www.anchorterminal.com/compare/kimi-k3-1-pro-vs-north-mini-code-1-0.md): D 48.6 vs C 61\n- [Kimi K3 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/kimi-k3-vs-north-mini-code-1-0.md): B 62.4 vs C 61\n- [Kolibri-1 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/kolibri-1-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Kronos vs North Mini Code 1.0](https://www.anchorterminal.com/compare/kronos-vs-north-mini-code-1-0.md): C 55.2 vs C 61\n- [Laguna M.1 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/laguna-m-1-vs-north-mini-code-1-0.md): C 56.7 vs C 61\n- [Laguna S 2.1 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Laguna XS 2.1 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [LBS-27B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/lbs-27b-vs-north-mini-code-1-0.md): C 55.8 vs C 61\n- [LFM2.5-2.6B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-north-mini-code-1-0.md): D 50.3 vs C 61\n- [LFM3-1.7B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [LFM3-Audio-2B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/lfm3-audio-2b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [LFM3-Omni-2B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/lfm3-omni-2b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [LFM3-VL-2B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/lfm3-vl-2b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Ling-3.0-tiny vs North Mini Code 1.0](https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-north-mini-code-1-0.md): C 56.2 vs C 61\n- [Ling-3.1-flash-1019 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/ling-3-1-flash-1019-vs-north-mini-code-1-0.md): C 54.8 vs C 61\n- [LongCat-2.5 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/longcat-2-5-vs-north-mini-code-1-0.md): D 50.5 vs C 61\n- [MiMo-V2.6 Distill Qwen 9B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [MiMo-V2.6-Flash-RL vs North Mini Code 1.0](https://www.anchorterminal.com/compare/mimo-v2-6-flash-rl-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [MiniCPM-o 4.5 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [MiniCPM-V 4.7 1B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/minicpm-v-4-7-1b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [MiniCPM-V 4.7 35B-A3B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/minicpm-v-4-7-35b-a3b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [MiniCPM5-2B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/minicpm5-2b-vs-north-mini-code-1-0.md): C 59.7 vs C 61\n- [MiniMax-M2.5 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/minimax-m2-5-vs-north-mini-code-1-0.md): C 59 vs C 61\n- [MiniMax-M2.7 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/minimax-m2-7-vs-north-mini-code-1-0.md): C 57.6 vs C 61\n- [MiniMax-M3.1-Flash vs North Mini Code 1.0](https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-north-mini-code-1-0.md): C 54.3 vs C 61\n- [Mistral Large 4 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/mistral-large-4-vs-north-mini-code-1-0.md): C 54.6 vs C 61\n- [Muse Glimmer 30B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-north-mini-code-1-0.md): BB 70 vs C 61\n- [Nanbeige4.2-3B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/nanbeige-4-2-3b-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Nanbeige4.3-33B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-north-mini-code-1-0.md): C 60.8 vs C 61\n- [NVIDIA Nemotron 3.5 Bolt E4B 4GB vs North Mini Code 1.0](https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-north-mini-code-1-0.md): C 61 vs C 61\n- [Nemotron 3.5 Lightning 30B A3B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-north-mini-code-1-0.md): B 64.7 vs C 61\n- [Nemotron 3 Nano 30B A3B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-north-mini-code-1-0.md): B 67.6 vs C 61\n- [Nemotron 3 Nano 4B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-north-mini-code-1-0.md): C 56.8 vs C 61\n- [Nemotron 3 Nano Omni 30B A3B Reasoning vs North Mini Code 1.0](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-north-mini-code-1-0.md): C 61.2 vs C 61\n- [Nemotron 3 Super 120B A12B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-north-mini-code-1-0.md): B 66.7 vs C 61\n- [Nemotron 3 Ultra 550B A55B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-north-mini-code-1-0.md): B 69.3 vs C 61\n- [North Mini Code 1.0 vs occamy-1.0](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-occamy-1-0.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-olmo-3-7b-think.md): C 61 vs D 52.3\n- [North Mini Code 1.0 vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-ornith-1-5-122b.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-ornith-1-5-35b-a3b.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-ornith-1-5-397b.md): C 61 vs C 59\n- [North Mini Code 1.0 vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-ornith-1-5-9b.md): C 61 vs C 61\n- [North Mini Code 1.0 vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-otel-2-0-llm-31b-it.md): C 61 vs C 56.8\n- [North Mini Code 1.0 vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen-agentworld-35b-a3b.md): C 61 vs D 52.1\n- [North Mini Code 1.0 vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-30b-a3b-instruct-2507.md): C 61 vs C 56.6\n- [North Mini Code 1.0 vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-4b-instruct-2507.md): C 61 vs C 54.5\n- [North Mini Code 1.0 vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-5-0-8b.md): C 61 vs D 46.7\n- [North Mini Code 1.0 vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-5-122b-a10b.md): C 61 vs B 63.1\n- [North Mini Code 1.0 vs Qwen3.5-2B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-5-2b.md): C 61 vs D 50.5\n- [North Mini Code 1.0 vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-5-397b-a17b.md): C 61 vs B 64.1\n- [North Mini Code 1.0 vs Qwen3.5-4B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-5-4b.md): C 61 vs C 61.2\n- [North Mini Code 1.0 vs Qwen3.5-9B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-5-9b.md): C 61 vs C 60.5\n- [North Mini Code 1.0 vs Qwen3.6-27B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-6-27b.md): C 61 vs B 66.7\n- [North Mini Code 1.0 vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-6-35b-a3b.md): C 61 vs B 62.7\n- [North Mini Code 1.0 vs Qwen3.8-27B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-8-27b.md): C 61 vs B 68.6\n- [North Mini Code 1.0 vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-8-flash-next.md): C 61 vs C 61.8\n- [North Mini Code 1.0 vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-coder-30b-a3b-instruct.md): C 61 vs C 55.7\n- [North Mini Code 1.0 vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-coder-next.md): C 61 vs C 57.6\n- [North Mini Code 1.0 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-omni-30b-a3b-instruct.md): C 61 vs E 41.8\n- [North Mini Code 1.0 vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-vl-2b-instruct.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-vl-30b-a3b-instruct.md): C 61 vs C 58\n- [North Mini Code 1.0 vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-vl-32b-instruct.md): C 61 vs C 56.4\n- [North Mini Code 1.0 vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-vl-4b-instruct.md): C 61 vs D 52.6\n- [North Mini Code 1.0 vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwen3-vl-8b-instruct.md): C 61 vs C 54.9\n- [North Mini Code 1.0 vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-qwopus3-8-27b-flash-v2.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Recursive Flint](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-recursive-flint.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-ripple-65b-preview.md): C 61 vs D 53.3\n- [North Mini Code 1.0 vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-sensenova-loop-9b-preview.md): C 61 vs D 46.8\n- [North Mini Code 1.0 vs SmolLM3-3B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-smollm3-3b.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-spark-x2-6-4b.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Step 3.7 Flash](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-step-3-7-flash.md): C 61 vs C 59.8\n- [North Mini Code 1.0 vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-swift-1-5-qwen3-8-27b.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-swift-1-5-qwen3-8-flash-next.md): C 61 vs C 54.2\n- [North Mini Code 1.0 vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-thinkingcap-qwen3-8-27b.md): C 61 vs C 61\n- [North Mini Code 1.0 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-unlimited-ocr-2.md): C 61 vs C 54.2\n- [North Mini Code 1.0 vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-wevisone-vl-2b.md): C 61 vs C 61\n- [North Mini Code 1.0 vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-wevisone-vl-4b.md): C 61 vs C 61\n- [North Mini Code 1.0 vs ZAYA1-8B](https://www.anchorterminal.com/compare/north-mini-code-1-0-vs-zaya1-8b.md): C 61 vs C 61\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on cohere.com or one of its subdomains. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"north-mini-code-1-0\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/north-mini-code-1-0\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/north-mini-code-1-0.svg\" alt=\"North Mini Code 1.0 on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![North Mini Code 1.0 on Anchor Terminal](https://www.anchorterminal.com/badges/north-mini-code-1-0.svg)](https://www.anchorterminal.com/tools/north-mini-code-1-0)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/north-mini-code-1-0\"\u003eNorth Mini Code 1.0 on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say North Mini Code 1.0 is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/north-mini-code-1-0-dark.png\n- Light: https://www.anchorterminal.com/assets/share/north-mini-code-1-0-light.png\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": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Open-weight models", "url": "https://www.anchorterminal.com/categories/open-weights" }, { "name": "North Mini Code 1.0", "url": "" } ], "description": "North Mini Code 1.0 is Cohere's open-weight coding agent model, a mixture of experts of 30B parameters with 3B active, trained for tool use, with interleaved thinking and a 256K context. Apache 2.0. Cohere's 4-bit build is 19 GB.", "facts": [ "#63 in Open weights", "None auth", "0 desk reviews" ], "h1": "North Mini Code 1.0", "image": "https://www.anchorterminal.com/assets/og/tools-north-mini-code-1-0.png", "path": "/tools/north-mini-code-1-0", "published": "2026-10-01", "section": "tools", "title": "North Mini Code 1.0 review (2026): pricing, alternatives and grade C", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/tools/north-mini-code-1-0" }, "tokens": { "markdown": 9800, "slim": 1580 }, "version": 1 }