Skip to content
llmwaves

North Mini Code (free)

Cohere · released Jun 17, 2026

Open weightsReasoningTool use

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...

Specification

Context window
256K
Max output
64K
Knowledge cutoff
Not stated
Parameters
30.5B
Licence
apache-2.0
Serving providers
1
Moderated
Yes
Uptime
97.0%

Intelligence

20.2

60th percentile

Coding

36.5

Coding Index

Agentic

3.1

Agentic Index

Output speed

26 t/s

Median across providers

Latency

1.18s

Time to first token

Cost per task

Free

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • GPQA Diamond
    75.7%
  • IFBench
    57.6%
  • SciCode
    38.2%
  • τ²-bench (Telecom)
    37.4%
  • AA-LCR (long context)
    36.0%
  • Terminal-Bench Hard
    31.1%
  • Humanity's Last Exam
    11.1%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
GPQA Diamond75.7%
IFBench57.6%
SciCode38.2%
τ²-bench (Telecom)37.4%
AA-LCR (long context)36.0%
Terminal-Bench Hard31.1%
Humanity's Last Exam11.1%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
R120.4
North Mini Code (free)20.2
GPT-5 Nano20.1
GLM 4.519.7
Kimi K2 071119.7
GPT-4.119.6
o3 Mini19.2
o1-pro19.1

Percentile among all indexed models

Intelligence60th
Coding49th
Agentic13th
Terminal work73th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
Free
Output / 1M tokens
Free
Cached input / 1M
Not offered
Blended 3:1
Free

One task, estimated

Free

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.