cohere/command-a-03-2025 Command A

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.

Released Date: 3/13/2025

Avg. Accuracy:

63.5%

Latency:

8.83s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CorpFin

54.5%

( 13 / 25 )

CaseLaw

79.7%

( 15 / 44 )

ContractLaw

67.7%

( 22 / 51 )

TaxEval

66.6%

( 18 / 31 )

Math500

76.2%

( 14 / 27 )

AIME

13.3%

( 15 / 23 )

MGSM

86.8%

( 16 / 25 )

LegalBench

78.7%

( 12 / 49 )

MedQA

80.5%

( 16 / 29 )

GPQA

29.3%

( 21 / 24 )

MMLU Pro

65.2%

( 18 / 24 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$2.50 / M Tokens

Output Cost

$10.00 / M Tokens

Input Cost (per char)

$0.65 / M chars

Output Cost (per char)

$2.94 / M chars

Join our mailing list to receive benchmark updates on

Stay up to date as new benchmarks and models are released.