Command A

Release Date: 3/13/2025

Benchmarked by Vals Logo
Vals Index

Accuracy (Vals Index)

17.90% ± 0.86

Latency (Vals Index)

359.99s

Cost/Test (Vals Index)

$1.16

Context Window

256k

Max Output Tokens

8k

Input Modality

Hyperparameter settings
Default Provider : Cohere

Temperature

0.3

Top P

Default

Top K

Default

Max Output Tokens

8,000

Benchmarks

Accuracy

Rankings

Vals Index

0.0%

± 0.86

32/ 32

CaseLaw (v2)

0.0%

± 1.09

10/ 37

CorpFin

0.0%

± 0.97

70/ 88

Finance Agent (v1.1)

0.0%

± 0.97

33/ 36

TaxEval (v2)

0.0%

± 0.95

78/ 96

AIME

0.0%

± 0.94

78/ 88

GPQA

0.0%

± 2.28

80/ 91

LiveCodeBench

0.0%

± 1.09

92/ 98

LegalBench

0.0%

± 0.42

50/ 110

MedQA

0.0%

± 0.36

71/ 94

MMLU Pro

0.0%

± 0.46

78/ 89

SWE-bench

0.0%

± 0.20

58/ 58

Terminal-Bench 2.0

0.0%

± 1.58

41/ 43

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.