Cohere model product
North Micro Vision
4B open-weight vision-language model from Cohere for image and document understanding tasks.
Updated Oct 23, 2026. Default version: North Micro Vision Instruct
LLMBoard Score0.0North Micro Vision Instruct
Coverage20%19 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
North Micro Vision Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
North Micro Vision Benchmark Results
Benchmark scores for North Micro Vision Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkInfoVQA | Score65.20% | Rank08 | Participants10 | Percentile22.22% | EvidenceC | Evaluated |
| BenchmarkCountBench | Score0.73 points | Rank09 | Participants9 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkRefCOCO-avg | Score0.73 points | Rank09 | Participants9 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMMMU (val) | Score32.90% | Rank13 | Participants13 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkHallusion Bench | Score61.50% | Rank14 | Participants20 | Percentile31.58% | EvidenceC | Evaluated |
| BenchmarkOCRBench-V2 (en) | Score36.70% | Rank15 | Participants15 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkBLINK | Score52.70% | Rank17 | Participants17 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkCharXiv-D | Score60.00% | Rank18 | Participants18 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkDocVQA | Score92.10% | Rank18 | Participants28 | Percentile37.04% | EvidenceC | Evaluated |
| BenchmarkMMBench-V1.1 | Score68.70% | Rank19 | Participants20 | Percentile5.26% | EvidenceC | Evaluated |
| BenchmarkChartQA | Score80.80% | Rank22 | Participants26 | Percentile16.00% | EvidenceC | Evaluated |
| BenchmarkOCRBench | Score79.20% | Rank24 | Participants24 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score37.30% | Rank25 | Participants25 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMMStar | Score51.80% | Rank26 | Participants27 | Percentile3.85% | EvidenceC | Evaluated |
| BenchmarkRealWorldQA | Score62.20% | Rank32 | Participants32 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAI2D | Score77.50% | Rank33 | Participants35 | Percentile5.88% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score74.90% | Rank62 | Participants70 | Percentile11.59% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score50.40% | Rank102 | Participants103 | Percentile0.98% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score30.70% | Rank140 | Participants142 | Percentile1.42% | EvidenceC | Evaluated |
North Micro Vision Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
North Micro Vision Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
North Micro Vision Runtime Performance
Provider-specific output speed and catalog latency for North Micro Vision Instruct. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
North Micro Vision Specifications
Technical details for the model's default version.
- Version
- North Micro Vision Instruct
- Released
- Aug 12, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 2.4B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
North Micro Vision Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionNorth Micro Vision Instruct | Released | LLMBoard0.00 | Parameters2.4B | ContextN/A | Max outputN/A | Open weightsYes | LicenseApache 2.0 |
Models similar to North Micro Vision
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
CO
Command R+
Cohere
CO
North Mini Code 1.0
Cohere
CO
Command A+
Cohere
OP
GPT-3.5-turbo
OpenAI
OP
GPT-5.1-Codex-Mini
OpenAI
IB
IBM Granite 4.0 Tiny
IBM
What is North Micro Vision?
Key information about North Micro Vision and its available data.
North Micro Vision combines a custom 400M SigLIP 2-based vision encoder with a 2B North Micro LLM backbone and supports native-resolution images, multilingual and multi-image inputs, and a 128K language-model context. It is intended for prototyping and fine-tuning, and is not a reasoning or tool-calling model.
Data as of 2026-10-22.
FAQ
Common questions about North Micro Vision.
When was North Micro Vision released?
North Micro Vision's default version was released on Aug 12, 2026.
How much does North Micro Vision cost?
No official standard PAYG price is currently available for North Micro Vision.
Who created North Micro Vision?
North Micro Vision was created by Cohere.
What is the context window for North Micro Vision?
A context window is not available for the default version.
Is North Micro Vision open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer North Micro Vision?
No provider offering is currently linked to the default version.