Command A

Release Date: 3/13/2025

Benchmarked by
Vals Index

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.

Avg. Accuracy

44.0%

Latency

57.0s

Cost (In/Out)

2.50 / 10.00

Context Window

256k

Max Output Tokens

8k

Input Modality

Benchmarks

Accuracy

Rankings

FinanceAgent

0.0%

43/ 43

CorpFin

0.0%

56/ 56

TaxEval

0.0%

73/ 73

Math500

0.0%

54/ 54

AIME

0.0%

63/ 63

MGSM

0.0%

66/ 66

LegalBench

0.0%

88/ 88

MedQA

0.0%

69/ 69

GPQA

0.0%

65/ 65

MMLU Pro

0.0%

63/ 63

LiveCodeBench

0.0%

62/ 62

Terminal-Bench

0.0%

28/ 28

SWE-bench

0.0%

24/ 24

Vals Index

0.0%

18/ 18

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Join our mailing list to receive benchmark updates

Model benchmarks are seriously lacking. With Vals AI, we report how language models perform on the industry-specific tasks where they will be used.

By subscribing, I agree to Vals' Privacy Policy.