New Finance Agent Benchmark Released
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:

58.6%

Latency:

16.51s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

FinanceAgent

4.3%

( 19 / 22 )

CorpFin

54.5%

( 20 / 35 )

CaseLaw

79.7%

( 22 / 55 )

ContractLaw

67.7%

( 26 / 62 )

TaxEval

66.6%

( 26 / 42 )

Math500

76.2%

( 23 / 38 )

AIME

13.3%

( 25 / 34 )

MGSM

86.8%

( 25 / 36 )

LegalBench

78.7%

( 18 / 60 )

MedQA

80.5%

( 23 / 40 )

GPQA

29.3%

( 32 / 35 )

MMLU Pro

65.2%

( 28 / 35 )

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)

$1.54 / M chars

Output Cost (per char)

$2.53 / M chars

Join our mailing list to receive benchmark updates on

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