# Command A+ Benchmark Scores & Performance

> Command A+ by Cohere scores 36.6/100 overall, ranking #143 out of 637 AI models.

Canonical page: https://benchlm.ai/models/command-a-plus

Last updated: September 30, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Cohere |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Overall Score | 36.6/100 |
| Overall Rank | #143 of 637 |

## Family & Coverage

- Family: Command A
- Variant: plus
- Benchmarks covered: 20 of 495
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [τ²-bench results](/benchmarks/tau2-bench) | 85% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 0.0% |
| [AA Agentic Index](/benchmarks/aaagenticindex) | 3.6% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 658 |
| [Terminal-Bench 2.1 (Vals)](/benchmarks/valsterminalbench21) | 17.6% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-SciCode](/benchmarks/aascicode) | 38.5% |
| [AA Coding Index](/benchmarks/aacodingindex) | 27.9% |

## Multimodal & Grounded Benchmarks

| Benchmark | Score |
|-----------|-------|
| [MMMU](/benchmarks/mmmu) | 75.1% |
| [MMMU-Pro](/benchmarks/mmmu-pro) | 63% |
| [CharXiv](/benchmarks/charxiv) | 52.7% |
| [AA-MMMU-Pro](/benchmarks/aammmupro) | 63.2% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 52.7% |
| [CritPt](/benchmarks/critpt) | 0.3% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 22.5% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 76.1% |
| [AA-HLE](/benchmarks/aahle) | 12.0% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -4.0% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 8.9% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 14.2% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-IFBench](/benchmarks/aaifbench) | 73.9% |

## Other Cohere Models

- [North Small Translate](/models/north-small-translate-1-0) - Score: not computed
- [North Micro Vision Instruct](/models/north-micro-vision-instruct) - Score: not computed
- [Cohere Transcribe Arabic 07-2026](/models/cohere-transcribe-arabic-07-2026) - Score: not computed
- [North Mini Code](/models/north-mini-code-1-0) - Score: not computed
- [Cohere Transcribe 03-2026](/models/cohere-transcribe-03-2026) - Score: not computed