North Mini Code 1.0
North Mini Code 1.0 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.
Key Specifications
Parameters
30.0B
Context
-
Release Date
June 9, 2026
Average Score
47.2%
Timeline
Key dates in the model's history
Announcement
June 9, 2026
Last Update
September 12, 2026
Today
September 19, 2026
Technical Specifications
Parameters
30.0B
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval
Benchmark Results
Model performance metrics across various tests and benchmarks
Programming
Programming skills tests
SWE-Bench Verified
SWE-Agent harness v1.1.0; average over 3 seeds • Self-reported
Other Tests
Specialized benchmarks
LiveCodeBench v6
LiveCodeBench v6 complex code-generation benchmark outside tool use; average over 3 seeds • Self-reported
SciCode
Complex code-generation benchmark outside tool use; average over 3 seeds • Self-reported
SWE-Bench Pro
SWE-Agent harness v1.1.0; average over 3 seeds • Self-reported
Terminal-Bench 2.0
Simple ReAct harness with a terminal-use tool based on Harbor Tmux; average over 3 seeds • Self-reported
Terminal-Bench Hard
Terminus-2 harness; average over 3 seeds • Self-reported
License & Metadata
License
apache_2_0
Announcement Date
June 9, 2026
Last Updated
September 12, 2026
Similar Models
All ModelsCommand R+
Cohere
104.0B
Best score:0.8 (MMLU)
Released:Aug 2024
Price:$0.25/1M tokens
Laguna XS 2.1
Poolside
33.0B
Released:Jul 2026
Price:$0.10/1M tokens
ERNIE 4.5
Baidu
21.0B
Best score:0.7 (GPQA)
Released:Jun 2025
Devstral Small 1.1
Mistral AI
24.0B
Released:Jul 2025
Price:$0.10/1M tokens
LongCat-Flash-Lite
Meituan
68.5B
Best score:0.9 (MMLU)
Released:Feb 2026
Jamba 1.5 Mini
AI21 Labs
52.0B
Best score:0.9 (ARC)
Released:Aug 2024
Price:$0.20/1M tokens
Nemotron 3 Nano (30B A3B)
NVIDIA
32.0B
Best score:0.8 (GPQA)
Released:Dec 2025
Price:$0.05/1M tokens
Mistral Small
Mistral AI
22.0B
Released:Sep 2024
Price:$0.20/1M tokens
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.