Cohere · Command A
Command A
Dense 111B enterprise Command model, now outscored by the cheaper open Command A+.
- AA Intelligence
- 7#124 of 142
- Input / output per 1M
- $2.50/ $10.00
- Output speed
- 53tok/s
- Context window
- 256K tokens
Composite indexes
- Artificial Analysis Intelligence Index#124 of 1427
Leader: Claude Opus 5.5 at 58
Coding
- LiveCodeBench#45 of 5628.7%
Leader: Fugu at 92.9%
Agents and tool use
- τ²-Bench#74 of 8815.2%
Leader: GLM-5.2 at 99.1%
Reasoning and knowledge
- GPQA Diamond#122 of 14252.7%
Leader: GPT-6 Astra at 96.1%
- Humanity’s Last Exam#139 of 1474%
Leader: Claude Opus 5.5 at 61.4%
- CritPt#121 of 1390%
Leader: GPT-5.6 Sol at 32.3%
Vision and long context
- AA Long Context Reasoning#114 of 13921.3%
Leader: Kimi K3 at 88.7%
Other published results
| Result | Score | Reported by | Source |
|---|---|---|---|
| aime-2025 · AIME 2025; non-reasoning | 13% | independent | Artificial Analysis: Command A ↗ |
| Terminal-Bench Hard (AA) · non-reasoning | 0.8% | independent | Artificial Analysis: Command A ↗ |
| IFBench · non-reasoning | 36.5% | independent | Artificial Analysis: Command A ↗ |
| AA-Omniscience Index · non-reasoning | -48.3 index | independent | Artificial Analysis: Command A ↗ |