Quality
#28/6722.5
Overall quality score
🇨🇦CohereOpen sourceCohere: Command A.
See how Cohere: Command A compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.
Speed
#36/6768 t/s
Output tokens per second
Input price
#59/67$2.50/1M
Per 1M tokens
Output price
#58/67$10.00/1M
Per 1M tokens
Context
#47/67256K
Content read at once
Comparison summary
Cohere: Command A ranks #28 of 67 for overall quality and #36 for response speed in the current catalogue.
Its listed input price is $2.50/1M, output price is $10.00/1M, and it can work with up to 256K of context at once.
Its strongest areas in the current data are coding, everyday help, math and logic.
Practical specifications
- Company
- Cohere
- Reasoning
- No
- Open weights
- Yes
- Input
- Text
- Output
- Text
- Context window
- 256K
Cohere: Command A technical benchmarks.
Named evaluation records for technical comparison. Results retain their original benchmark names and sources.
| Benchmark | Area | Command A | Source |
|---|---|---|---|
| Intelligence Index | overallQuality | 22.5 | OpenRouter / artificial-analysis |
| Coding Index | coding | 27.8 | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 9.2 | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 76.1 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 11.4 | OpenRouter model benchmarks |
| IFBench | IFBench | 73.9 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 80.7 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 46 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 10.9 | OpenRouter model benchmarks |
| CritPt | CritPt | 0.3 | OpenRouter model benchmarks |
| SciCode | SciCode | 37.8 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 25 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 8.8 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 85.9 | OpenRouter model benchmarks |
Quality benchmarks
See where Cohere: Command A stands.
The darker bar marks Cohere: Command A; the lighter bars provide context from other leading models.
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better