Command A
| Released | 2025-03-13 |
|---|---|
| Price per 1M | $2.50 in · $10.00 out |
| Overall score | 36.7 · rank 209 |
| Context window | 256,000 tokens |
| Provider | Cohere |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 36.7 | 209 | 7 |
| Overall: Coding | 35.8 | 203 | 5 |
| Overall: Reasoning | 34.1 | 222 | 3 |
| Overall: Agentic work | 38.9 | 196 | 5 |
| Overall: Frontend | 33.6 | 209 | 2 |
| Coding | 33.6 | 196 | 2 |
| Agents | 42.0 | 151 | 1 |
| Reasoning | 35.7 | 220 | 2 |
| Knowledge | 30.6 | 160 | 1 |
| General | 41.9 | 153 | 1 |
| Value vs price | −15.4 | 189 |
Evidence
Coding 33.6 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 7.8% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 35.1% | Vals AI | 2026-09-01 |
Agents 42.0 ±3.6
Reasoning 35.7 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond (Vals run) | 48.5% | Vals AI | 2026-09-01 |
| Kagi Reasoning Benchmark | 28.8% | Kagi | 2026-11-11 |
Knowledge 30.6 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 69.2% | Vals AI | 2026-09-01 |
General 41.9 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,354 | LMArena | 2026-11-09 |
Names matched to this model
command-a, command-a-03-2025