Skip to content
ModelCap

North Mini Code

Current board #95Official publisher releaseOpen weightsFree tier

Cohere·cohere/north-mini-code

North Mini Code is ModelCap current-board rank #95 with Index 51.9 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.

North Mini Code listed OpenRouter input price is Free per 1M tokens and listed output price is Free per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.

North Mini Code has a published context limit of 256K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.

North Mini Code has 1 published OpenRouter serving endpoint, from OpenRouter as of 22 Sept 2026, 02:49 UTC.

North Mini Code weight access is open weights, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
51.9#95
Measured · 20% support · score interval 32.1–71.7
Evidence as of 17 Sept 2026, 06:41 UTC
Market Gravity
25.7
Secondary market signal
Input
Free
per 1M tokens
Output
Free
per 1M tokens
Context
256K
tokens
Providers
1
endpoint
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
CohereFreeFree256K97.87%

Reported evaluation leads (3)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
harborframework/terminal-bench-2.0
terminalbench_2
36
Unpinned
not published
Reported
Quarantined
ScaleAI/SWE-bench_Pro
SWE_Bench_Pro
40.2
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Verified
swe_bench_%_resolved
67.6
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
51.9
Measured · 1 public benchmark observation across 1 board
Current board
#95
Public rank basis
Measured (measured)
Index support
20.0% · limited
Index interval
32.1–71.7
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
17 Sept 2026, 06:41 UTC
Identity binding
Exact catalogue product · cohere/cohere/north-mini-code · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata CohereLabs/North-Mini-Code-1.0@d11e61a842617a22dc328552fa5bb86231ee4f37 (not the evaluation revision)
Index observations used
1
Qualified Index evidence point
51.9
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
51.9
Evidence status
provisional · 50% mass
General preference
51.9
Coding
Agents & tools
Reasoning
Evidence breadth
80%
Evidence coverage
20%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
27.7
Liquidity (providers × uptime)
20.1
Open reach (HF downloads)
12.8
Surface (context / tools / modalities)
75.1
Freshness
69.3
  • · OpenRouter popularity #65
  • · 1 live provider
  • · HF 30d downloads 11190
  • · Catalogue: context 256000, reasoning, tools
  • · First seen 2026-06-17

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
75.2
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
73.6
Evaluation provenance
37.9

Missing: artifactReproducibility.base-lineage, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
25.7
OpenRouter weekly popularity
#65 of 322

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

No matched Arena rating

This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.

Market Gravity breakdown

Usage55%
27.7

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
20.1

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
12.8

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
69.3

Time since first public availability, on a six-month half-life.

Specification

Context window
256K tokens
Max output
64K tokens
Inputs
Text
Outputs
Text
Tokenizer
Cohere
Cached input tokens
Not offered
First seen on OpenRouter
17 Jun 2026

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
apache-2.0
Pinned revision
d11e61a84261
Parameters
30.5B
Architecture
Cohere2MoeForCausalLM
Model type
cohere2_moe
Hugging Face downloads (30d)
11K
Downloads (all time)
81K
Likes
567
Repository updated
15 Jun 2026, 04:32 UTC

Compare North Mini Code with

Pick any model

Benchmark leaderboards featuring North Mini Code

All leaderboards
Public benchmark boards on which North Mini Code has a published result
LeaderboardScoreSource rankConfigurationPublished
Artificial Analysis Intelligence IndexArtificial Analysis9.9#131 of 151intelligence-index:v4.3:reasoning-unspecified17 Sept 2026
τ²-Bench Telecom (Artificial Analysis run)Artificial Analysis37.4%#237 of 436tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="North Mini Code":reasoning=true5 Sept 2026
Humanity's Last Exam (Artificial Analysis run)Artificial Analysis11.1%#269 of 615hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="North Mini Code":reasoning=true5 Sept 2026

Alternatives to North Mini Code, by the numbers

Ranked neighbours

Models within 3 places of #95 on the ModelCap Index.

Other ranked Cohere models

The same publisher's other current models with a public Index position.

North Mini Code: common questions

How does North Mini Code rank among AI models?

North Mini Code holds ModelCap Index position #95 of 248 ranked language models as of 22 September 2026, with an Index score of 51.9 (interval 32.1–71.7); evidence: measured. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does North Mini Code cost per 1M tokens?

North Mini Code is listed at Free per 1M input tokens and Free per 1M output tokens as of 22 September 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh; at least one provider lists a free tier. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply Free total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of North Mini Code?

North Mini Code has a published context window of 256K tokens (256,000) and a maximum output of 64K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.

Is North Mini Code open-weight?

Open weights (apache-2.0). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is CohereLabs/North-Mini-Code-1.0 on Hugging Face.

Which API providers serve North Mini Code?

One provider serves North Mini Code through OpenRouter as of 22 September 2026: Cohere. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

Which benchmarks has North Mini Code been evaluated on?

North Mini Code has published results on 3 public boards tracked by ModelCap as of 22 September 2026: AA Intelligence Index 9.9 (#131 of 151), AA τ²-Bench Telecom 37.4% (#237 of 436) and AA Humanity's Last Exam 11.1% (#269 of 615). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

How does North Mini Code compare with Qwen3 VL 235B A22B Thinking?

North Mini Code ranks #95 (Index 51.9) and Qwen3 VL 235B A22B Thinking ranks #94 (Index 52.1) on the ModelCap Index as of 22 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was North Mini Code released?

North Mini Code first appeared in the catalogue on 17 Jun 2026. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.