name = "North Mini Code"
description = "Cohere coding model for practical software engineering and agentic edits"
family = "north"
release_date = "2026-06-09"
last_updated = "2026-06-09"
attachment = false
reasoning = true
temperature = true
structured_output = true
knowledge = "2025-09-23"
tool_call = true
open_weights = true

[limit]
context = 256_000
output = 64_000

[modalities]
input = ["text"]
output = ["text"]

[[benchmarks]]
name = "SWE-Bench Verified"
score = 67.6
metric = "resolved"
harness = "SWE-agent"
source = "https://huggingface.co/CohereLabs/North-Mini-Code-1.0"
date = "2026-06-09"

[[benchmarks]]
name = "SWE-Bench Pro"
score = 40.2
metric = "resolve rate"
harness = "SWE-agent"
source = "https://huggingface.co/CohereLabs/North-Mini-Code-1.0"
date = "2026-06-09"

[[benchmarks]]
name = "Artificial Analysis Intelligence Index"
score = 27.6
metric = "index score"
source = "https://artificialanalysis.ai/articles/north-mini-code-cohere-s-small-coding-focused-moe-model"
date = "2026-06-09"

[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 33.4
metric = "index score"
source = "https://artificialanalysis.ai/articles/north-mini-code-cohere-s-small-coding-focused-moe-model"
date = "2026-06-09"

[[benchmarks]]
name = "GDPval-AA"
score = 14
metric = "win rate"
source = "https://artificialanalysis.ai/articles/north-mini-code-cohere-s-small-coding-focused-moe-model"
date = "2026-06-09"

[[benchmarks]]
name = "τ²-Bench Telecom"
score = 37
metric = "success rate"
source = "https://artificialanalysis.ai/articles/north-mini-code-cohere-s-small-coding-focused-moe-model"
date = "2026-06-09"