Compare Models
Command A

Release Date: Mar 13, 2025

Developer Cohere 🇨🇦
Context Window 256k
Max Output Tokens 8k
Token Costs (in/out) $2.50/10.00
Weights Private
Input Modalities

Accuracy

43.41 %

Avg. Cost (In/Out)

$ 2.50 / $ 10.00

Latency

2 min 28 s

Vals Index
BenchmarksAccuracyRankings
TaxEval v2

0.0%

±0.95
120/140
GPQA Diamond

0.0%

±2.28
120/133
LiveCodeBench

0.0%

±1.09
132/138
LegalBench

0.0%

±0.42
83/137
MMLU Pro

0.0%

±0.46
120/133
SWE-bench

0.0%

±1.20
83/83
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : Cohere
Temperature: 0.3
Top P: Default
Top K: Default
Max Output Tokens: 8,000

Updates

Mar 24, 2025

We just evaluated Command A on all benchmarks!

  • Command A is Cohere’s most efficient and performant model to date, specializing in agentic AI, multilingual, and human evaluations for real-life use cases.
  • On our proprietary benchmarks, Command A shows mixed performance, ranking 23rd out of 28 models on TaxEval but a good 10th out of 22 models on CorpFin.
  • The model performs better on some academic benchmarks, scoring 78.7% on LegalBench (9th place) and 86.8% on MGSM (13th place).
  • However, it struggles with AIME (13.3%, 12th place) and GPQA Diamond (29.3%, 18th place).