Qwen 3 Max Preview

Release Date: 9/5/2025

Benchmarked by Vals Logo

Preview of the largest and most recent Qwen Model

Avg. Accuracy

59.77%

Latency

388.35s

Cost (In/Out)

1.2 / 6

Context Window

262k

Max Output Tokens

66k

Input Modality

Benchmarks

Accuracy

Rankings

CaseLaw (v2)

0.0%

57/ 57

CorpFin

0.0%

80/ 80

Finance Agent

0.0%

55/ 55

TaxEval (v2)

0.0%

86/ 86

AIME

0.0%

76/ 76

GPQA

0.0%

77/ 77

IOI

0.0%

40/ 40

LiveCodeBench

0.0%

84/ 84

LegalBench

0.0%

100/ 100

MedQA

0.0%

84/ 84

MGSM

0.0%

73/ 73

MMLU Pro

0.0%

78/ 78

SWE-bench

0.0%

43/ 43

Terminal-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.