Quality
Highest overall scores
- 1
Cohere: Command A22.8 - 2Cohere: Command R+ (08-2024)0
- 3Cohere: Command R7B (12-2024)0
Cohere model benchmarks.
Compare Cohere models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1Cohere: Command A27 t/s
- 2Cohere: Command R7B (12-2024)20 t/s
- 3Cohere: Command R+ (08-2024)8 t/s
Input price
Lowest price per 1M tokens
- 1Cohere: Command R7B (12-2024)$0.04/1M
- 2Cohere: Command A$2.50/1M
- 3Cohere: Command R+ (08-2024)$2.50/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare Cohere model capability.
Performance and price
Compare practical tradeoffs.
All Cohere models.
3 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| Cohere: Command A | 22.8 | 27 t/s | 256K | $2.50 | $10.00 | |
| Cohere: Command R+ (08-2024) | 0 | 8 t/s | 128K | $2.50 | $10.00 | |
| Cohere: Command R7B (12-2024) | 0 | 20 t/s | 128K | $0.04 | $0.15 |
Cohere technical benchmarks.
Compare named evaluation records available for Cohere models. Missing results remain blank rather than being estimated.
| Benchmark | Area | Command A | Command R+ (08-2024) | Command R7B (12-2024) | Source |
|---|---|---|---|---|---|
| Intelligence Index | overallQuality | 22.8 | — | — | 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 | 12 | — | — | 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 | 48.7 | — | — | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 10.8 | — | — | 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 | 8.9 | — | — | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 85.8 | — | — | OpenRouter model benchmarks |