71.2%
MMLU-Pro (AA run)
Models / Cohere
Command · Released 2026-03-15
Cohere's enterprise-focused Command tier. Strong at RAG, tool use, and multilingual retrieval workflows. 256K context.
Pick when your stack already uses Cohere embed + rerank and you want one vendor for retrieval pipelines.
Family profile
Best published score in each covered benchmark family.
7 tested benchmark families
Where Command A places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| AA output speed | Performance | #10/ 187 | Artificial Analysis | 2026-09-01 | |
| MATH | Math | #19/ 25 | 82 | Artificial Analysis | 2026-09-01 |
| LiveCodeBench | Coding | #30/ 31 | 29 | Artificial Analysis | 2026-09-01 |
| AIME | Math | #36/ 37 | 13 | Artificial Analysis | 2026-09-01 |
| MMLU-Pro | Knowledge | #38/ 39 | 71 | Artificial Analysis | 2026-09-01 |
| AA time to first token | Performance | #85/ 186 | Artificial Analysis | 2026-09-01 | |
| τ³-Bench Banking | Agentic | #98/ 106 | 6 | Artificial Analysis | 2026-09-01 |
| SciCode | Coding | #145/ 180 | 38 | Artificial Analysis | 2026-09-01 |
| Humanity's Last Exam | Reasoning | #149/ 180 | 12 | Artificial Analysis | 2026-09-01 |
| GPQA Diamond | Reasoning | #150/ 185 | 76 | Artificial Analysis | 2026-09-01 |
| AA-LCR | Long context | #152/ 179 | 49 | Artificial Analysis | 2026-09-01 |
| Artificial Analysis Intelligence Index | Reasoning | #162/ 187 | 23 | Artificial Analysis | 2026-09-01 |
| Terminal-Bench | Agentic | #165/ 184 | 23 | Artificial Analysis | 2026-09-01 |
The three highest-scoring models with pages in each capability family. Where Command A shows up, it's highlighted.
Benchmark rows added to the public ledger for Command A in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA-LCR | Long context | 48.67% | Artificial Analysis | 5 |
| AA output speed | Performance | 228 t/s | Artificial Analysis | 5 |
| AA time to first token | Performance | 0.16s | Artificial Analysis | 5 |
| AIME | Math | 13% | Artificial Analysis | 5 |
| Artificial Analysis Intelligence Index | Reasoning | 22.8% | Artificial Analysis | 5 |
| GPQA Diamond | Reasoning | 76.1% | Artificial Analysis | 5 |
| Humanity's Last Exam | Reasoning | 12% | Artificial Analysis | 5 |
| LiveCodeBench | Coding | 28.7% | Artificial Analysis | 5 |
| MATH | Math | 81.87% | Artificial Analysis | 5 |
| MMLU-Pro | Knowledge | 71.2% | Artificial Analysis | 5 |
| SciCode | Coding | 37.8% | Artificial Analysis | 5 |
| τ³-Bench Banking | Agentic | 5.98% | Artificial Analysis | 5 |
| Terminal-Bench | Agentic | 22.85% | Artificial Analysis | 5 |
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
Every catalog benchmark for Command A. Scores link to the original source; gaps mean no public row exists yet.
14 of 37 catalog benchmarks have a sourced row for Command A.
71.2%
MMLU-Pro (AA run)
22.8%
AA Intelligence Index v4.1
76.1%
GPQA Diamond (AA run)
12%
HLE (AA run)
28.7%
LiveCodeBench (AA run)
37.8%
SciCode (AA run)
22.85%
Terminal-Bench v2.1 (AA run)
5.98%
τ³-Bench Banking (AA run)
48.67%
AA-LCR (AA run)
70.6%
BFCL
228 t/s
Median output tokens/s (1k prompt, default provider)
0.16s
Median time to first token (1k prompt, default provider)