Qwen 3 Max

Release Date: 9/23/2025

Benchmarked by Vals Logo
Vals Index

Largest and most recent Qwen Model

Avg. Accuracy

58.82%

Latency

638.33s

Cost (In/Out)

1.2 / 6

Context Window

262k

Max Output Tokens

66k

Input Modality

Hyperparameter settings
Default Provider : Alibaba

Temperature

0.7

Top P

Default

Top K

Default

Max Output Tokens

65,536

Benchmarks

Accuracy

Rankings

Vals Index

0.0%

20/ 28

CaseLaw (v2)

0.0%

45/ 63

CorpFin

0.0%

43/ 82

TaxEval (v2)

0.0%

19/ 91

Vibe Code Bench

0.0%

12/ 16

AIME

0.0%

32/ 82

GPQA

0.0%

23/ 85

IOI

0.0%

14/ 43

LiveCodeBench

0.0%

29/ 90

LegalBench

0.0%

30/ 104

MedQA

0.0%

53/ 90

MGSM

0.0%

25/ 75

MMLU Pro

0.0%

20/ 84

SWE-bench

0.0%

22/ 50

Terminal-Bench

0.0%

29/ 47

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.