Models / Cohere

Command A

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.

#143 of 168 on AA Index · current snapshot
23 AA Index · 14 benchmark rows · 2 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite40
Context256K
Input / 1M$2.5
Output / 1M$10
Knowledge cutoff2025-06-01
Output speed228 t/s
TTFT (default API)0.16s
Statussolid

Family profile

Best published score in each covered benchmark family.

59/100 avg
Knowledge
71
Reasoning
76
Math
82
Coding
38
Agentic
23
Long context
49
Tool use
71

7 tested benchmark families

Benchmark placements

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.

BenchmarkFamilyRankScoreSourceDate
AA output speedPerformance#10/ 187Artificial Analysis2026-09-01
MATHMath#19/ 2582Artificial Analysis2026-09-01
LiveCodeBenchCoding#30/ 3129Artificial Analysis2026-09-01
AIMEMath#36/ 3713Artificial Analysis2026-09-01
MMLU-ProKnowledge#38/ 3971Artificial Analysis2026-09-01
AA time to first tokenPerformance#85/ 186Artificial Analysis2026-09-01
τ³-Bench BankingAgentic#98/ 1066Artificial Analysis2026-09-01
SciCodeCoding#145/ 18038Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#149/ 18012Artificial Analysis2026-09-01
GPQA DiamondReasoning#150/ 18576Artificial Analysis2026-09-01
AA-LCRLong context#152/ 17949Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#162/ 18723Artificial Analysis2026-09-01
Terminal-BenchAgentic#165/ 18423Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Command A shows up, it's highlighted.

Newest receipts

Benchmark rows added to the public ledger for Command A in the last 120 days. Older rows live in the full table below.

13 recent
Family coverage

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.

Knowledge71
Reasoning76
Math82
Coding38
Agentic23
Long context49
Tool use71
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Command A. Scores link to the original source; gaps mean no public row exists yet.

14 sourced rows

14 of 37 catalog benchmarks have a sourced row for Command A.

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Tool use

Performance

Sources