Cohere model product
0 is Cohere's open-weights sparse Mixture-of-Experts coding model optimized for code generation, agentic software engineering, terminal tasks, and local deployment.
Updated Aug 17, 2026. Default version: North Mini Code 1.0
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for North Mini Code 1.0.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkTerminal-Bench Hard | Score31.1% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score38.2% | Rank15 | Participants21 | Percentile30.0% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score70.3% | Rank30 | Participants56 | Percentile47.3% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score40.2% | Rank50 | Participants50 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score36.0% | Rank50 | Participants51 | Percentile2.0% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score67.6% | Rank74 | Participants111 | Percentile33.6% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for North Mini Code 1.0. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionNorth Mini Code 1.0 | Released | LLMBoard36.4 | Parameters30B | ContextN/A | Max outputN/A | Open weightsNo | LicenseApache 2.0 |
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about North Mini Code 1.0 and its available data.
0 is Cohere's open-weights sparse Mixture-of-Experts coding model optimized for code generation, agentic software engineering, terminal tasks, and local deployment.
It has 30B total parameters with 3B active parameters, 128 experts with 8 active per token, native tool-use support, interleaved thinking, a 256K context length, and up to 64K output tokens.
Data as of 2026-08-17.
Common questions about North Mini Code 1.0.
North Mini Code 1.0's default version was released on Jun 9, 2026.
No official standard PAYG price is currently available for North Mini Code 1.0.
North Mini Code 1.0 was created by Cohere.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.
Nearby ranked alternatives include Gemma 4 12B, Nemotron 3.5 Lightning, Kimi K2.