CohereNorth Mini Code
North Mini Code is a Cohere open-weights reasoning model, released 9 Jun 2026. Its best configuration ranks #506 of 785 on the BenchLeader Index at 45.9 ±6.9, in the lower half. The ± is the point: 407 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (58) and lowest in knowledge (40). Output speed of 60 tokens per second puts it slower than most, with a first answer in 33.6 s. Last measured 9 Jun 2026.
- Blended price
- –
- Output speed
- 60 tok/s
- measured by Artificial Analysis
- First answer
- 34 s
- Context
- 256k
- Full answer
- 42 s
- median, reasoning included
- Cost per run
- –
- Released
- 9 Jun 2026
- Overall index46
- Reasoning41
- Agents & tools43
- Knowledge40
- Instruction following58
- Long context43
- Composite41
Versions
Cohere has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| North Mini Codethis page | 9 Jun 2026 | 45.9 | #506 |
| North Mini Code 1.0 | 9 Jun 2026 | – | – |
How its index has moved
9 Sept 2026 to 23 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 75.7%#246 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 11.1%#301 | Artificial Analysis | |
| CritPt | 0.3%#271 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode (AA)not in index | 38.8%#184 | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | 0.5%#139 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 35.6%#147 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 31.1%#106 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 37.4%#226 | Artificial Analysis | |
| GDPval-AA v2.1not in index | 0.0%#124 | Artificial Analysis | |
| τ³-Banking (AA) | 6.4%#167 | Artificial Analysis | |
| AutomationBenchnot in index | 1.5%#189 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 1.8%#192 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -48.6#378 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 18.9%#324 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 16.8%#322 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 57.5%#138 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 37.3%#368 | Artificial Analysis | |
| MLCRnot in index | 4.4%#152 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 9.9#386 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | – | – | 38.6 s |
| Summarize a 30-page report | 12,000 / 600 | – | – | 43.6 s |
| Code edit | 6,000 / 1,500 | – | – | 58.5 s |
| Agentic coding session | 60,000 / 4,000 | – | – | 1.7 min |
| Structured extraction | 2,000 / 200 | – | – | 37.0 s |
See also
Questions people ask
- What are North Mini Code's benchmark scores?
- As of 25 Oct 2026, North Mini Code scores 45.9 ±6.9 on the BenchLeader Index, strongest in instruction following (58) and weakest in knowledge (40). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
- How does North Mini Code rank?
- North Mini Code is #506 of 785 ranked configurations on 25 Oct 2026. 407 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was North Mini Code released?
- Cohere released North Mini Code on 9 Jun 2026.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “North Mini Code: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/north-mini-code.