Claude Sonnet 4 (Nonthinking)

Release Date: 5/22/2025

Benchmarked by Vals Logo

Balanced high-performance AI for coding, agents, and production workloads, with extended context and reasoning.

Avg. Accuracy

63.21%

Latency

241.76s

Cost (In/Out)

3 / 15

Context Window

200k

Max Output Tokens

64k

Input Modality

Benchmarks

Accuracy

Rankings

CaseLaw (v2)

0.0%

59/ 59

CorpFin

0.0%

82/ 82

Finance Agent

0.0%

57/ 57

MortgageTax

0.0%

56/ 56

SAGE

0.0%

36/ 36

TaxEval (v2)

0.0%

87/ 87

AIME

0.0%

78/ 78

GPQA

0.0%

79/ 79

IOI

0.0%

42/ 42

LiveCodeBench

0.0%

86/ 86

LegalBench

0.0%

102/ 102

MATH 500

0.0%

60/ 60

MedQA

0.0%

86/ 86

MGSM

0.0%

75/ 75

MMLU Pro

0.0%

80/ 80

MMMU

0.0%

55/ 55

SWE-bench

0.0%

45/ 45

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.