Command A
Command A is behind the leaders in factuality. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multimodal tasks, multilingual tasks, or instruction following.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Coding, Agentic, Safety, Long Context, Math, Multimodal, Multilingual or Instruction Following.
Price
$2.50input$10.00outputper million tokens
From Artificial Analysis · 2 providers tracked · All prices
Evidence
21results on20benchmarks
- 6 independently verified
- 15 aggregator
From 4 sources · latest Oct 8, 2026 · How verification works
API features
Structured outputs
As listed by OpenRouter
Research
4 papers reference Command ACommand A benchmark results
21 results on 20 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
39.1% behind the leader3 of 4 ranked benchmarks measured
- 9.30May 2, 2026
- AA-Omniscience · Non-hallucination22.68Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy16.38Oct 8, 2026omniscienceAccuracy
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond52.73Oct 8, 2026gpqa
- Humanity's Last Exam4.03Oct 8, 2026aa_hle
0 of 10 ranked benchmarks measured
- Terminal-Bench Hard0.76Oct 8, 2026aa_terminalbench_hard
- SciCode28.13Sep 4, 2026aa_scicode
0 of 7 ranked benchmarks measured
- 0.00Jun 15, 2026
0 of 3 ranked benchmarks measured
- 21.33Oct 8, 2026
0 of 3 ranked benchmarks measured
- IFBench36.46Oct 8, 2026aa_ifbench
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence7.00Aug 29, 2026Artificial Analysis Intelligence Index
- livebench_language36.70Aug 23, 2026livebench_language@2025-04-07
- vectara_avg_summary_length101.70May 2, 2026Average Summary Length (Words)
- vectara_answer_rate97.60May 2, 2026Answer Rate
- vectara_factual_consistency90.70May 2, 2026Factual Consistency Rate
- τ²-Bench Telecom (AA run)15.20Oct 8, 2026aa_tau2
Show 4 more resultsHide 4 results
- 5.07Jun 18, 2026
- AA Intelligence6.96Oct 8, 2026aa_intelligence_index
- -48.27Oct 8, 2026
- 9.88Jun 18, 2026
Command A: common questions
Who makes Command A?
Command A is made by Cohere.
When was Command A released?
Command A was released on Mar 13, 2025, according to Artificial Analysis.
What is Command A good at?
Command A is behind the leaders in factuality. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multimodal tasks, multilingual tasks, or instruction following.
How much does Command A cost?
Command A costs $2.50 per million input tokens and $10.00 per million output tokens, according to Artificial Analysis. We track its price at 2 providers. At a mix of three input tokens to one output token, it costs more than 85% of the 331 priced models we track.
How many benchmarks has Command A been tested on?
We track 21 results for Command A on 20 benchmarks from 4 sources, 6 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does Command A support?
OpenRouter lists structured outputs for Command A.
About this record
Where Command A's numbers come from, and every name it appears under.
- Tracked since
- Apr 27, 2026
- Newest source mention
- Sep 2, 2026
Where the results come from
Verification: 21 scores · 6 independently verified · 15 aggregator-attributed. How these tiers are assigned
From 4 sources on 3 sites. Artificial Analysis supplies 16 of them; the 6 independently verified results come from 3 sites. Bars are coloured by trust tier.
- artificialanalysis.ai16
- raw.githubusercontent.com4
- huggingface.co1