Model record
Command A model overview
Command A is a open weights model from Cohere. It was released on March 13, 2025. Its strongest case is purpose-built rag behavior, while buyers should account for weights restrict commercial use.
Command A benchmark snapshot
| Evaluation | Reported score | What it probes |
|---|---|---|
| MMLU-Pro | 75.8 | Broad knowledge and multi-step reasoning |
| GPQA Diamond | 54.6 | Graduate-level science reasoning |
| SWE-bench Verified | Not reported | Verified real-repository issue resolution |
| LiveCodeBench | 36.2 | Contamination-aware competitive programming |
| SWE-Bench Pro | Not reported | Longer, harder professional software tasks |
| Artificial Analysis Intelligence Index | Not reported | Composite third-party capability index; version matters |
Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.
Command A strengths
- Purpose-built RAG behavior
- Tool-use and agent workflows
- Broad enterprise language coverage
Command A limitations
- Weights restrict commercial use
- Not optimized for consumer creative tasks
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.
Source record
Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.
Read Cohere model announcement ↗