Ctrl K
Back to models

Cohere

North Mini Code

  • Released
  • Open weights
  • Apache 2.0
  • Free OpenRouter API · limits apply
Compare
Intelligence Index

Reasoning setting

9.9#72 of 83measured models
Measured · Artificial Analysis v4.3.2
API price from
$0.00 in / $0.00 out / 1M tokOpenRouter · Cohere
Context window
256K tok

Performance profile

ReasoningRank #62 of 107
75.7%
GPQA Diamond
CodingRank #69 of 94
38.8%
SciCode

Capabilities

Context window

Modalities

Measured setting

Integration

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
North Mini Code
Cost per task (USD) · log scale
North Mini CodeReasoning
Intelligence Index
9.9
Cost / task
$0.00
Evaluation time
3.3m
Rate-limited free API

Pricing & access

API route
OpenRouter · CohereFree · rate limited
Tier & contextStandard

USD per 1M tokens

Input
$0.00
Output
$0.00

This free OpenRouter route is rate limited. Model Vault and local hardware costs are separate. OpenRouter limits (opens in a new tab)

Run locally

GGUF
Context
Estimated memory

~20.6 GiB

RAM + VRAM

Estimate assumptions

One text chat at the selected context, with a 16-bit cache and app allowance. Operating system and image processing are extra; optimized caches can use less.

32 GiB RAMwithout GPU offload

Memory budgetOne text chat
Weights
17.9 GiB
Context cache
0.8 GiB16-bit cache
App allowance
2 GiB
Download
19.2 GB
Disk space
~27 GB
Available software
llama.cpp (opens in a new tab)
Custom llama.cpp build required (opens in a new tab)
Get GGUF (opens in a new tab)
vLLM setup (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

North Mini Code · Reasoning#87 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 84Nova 2.0 LiteHigh11.6%
  6. 85NVIDIA Nemotron 3 Nano 30B A3BReasoning11.4%
  7. 86Granite 4.2 30BReasoning11.2%
  8. 87North Mini CodeReasoning11.1%
  9. 88gpt-oss-20bHigh11.0%
  10. 89Hermes 4 - Llama-3.1 405BReasoning10.9%
  11. 90Nemotron 3.5 LightningReasoning10.6%

Peers use their best measured result on this benchmark.

Alternatives

Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.