Context
256K tokens (~128 books)
Input $/1M
Free
Output $/1M
Free
Type
text
License
Open Source
Benchmarks
10 tested
Data as of
About
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
Tested on 10 benchmarks. Top scores: Artificial Analysis · GPQA Diamond (75.7%), Artificial Analysis · IFBench (57.6%), Artificial Analysis · SciCode (38.8%).
Capabilities
speed
29.9
#86 globally
Benchmark Scores
Compare AllTested on 10 benchmarks · Ranked across 1 categories
Score Distribution (all 312 models)
0255075100
speedCompare speed →
Quick compare:
vs Qwen3 Coder Next FP8vs Qwen2.5 Coder 32B Instruct AWQ
P
vs Speaker Diarization Community 1 Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
Source Code
BenchGecko API
north-mini-code-free
Specifications
- Typetext
- Context256K tokens (~128 books)
- ReleasedJun 2026
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.000
Available On
Categories
Share & Export
Frequently Asked Questions
North Mini Code (free) is an open-source text AI model by Cohere, released in June 2026. Context window: 256K tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenKey facts · as of 2026-06-22
- North Mini Code (free) by Cohere. Not enough public benchmark scores to rank yet.
- List price free input · free output per 1M tokens (as of 2026-06-22).
How to cite · data as of 2026-06-22
North Mini Code (free) · benchmarks, pricing and providers. BenchGecko, data as of 2026-06-22. https://benchgecko.ai/model/north-mini-code-free
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP