Models

Release date

Models

Qwen 3 Max Thinking

Release Date: 1/23/2026

Benchmarked by Vals Logo

Qwen 3 Max with enhanced reasoning capabilities

Avg. Accuracy

58.06%

Latency

468.74s

Cost (In/Out)

1.2 / 6

Context Window

256k

Max Output Tokens

32k

Input Modality

Benchmarks

Accuracy

Rankings

0.0%

14/ 33

0.0%

14/ 33

0.0%

48/ 60

0.0%

48/ 60

0.0%

2/ 79

0.0%

2/ 79

0.0%

18/ 58

0.0%

18/ 58

0.0%

9/ 82

0.0%

9/ 82

0.0%

16/ 81

0.0%

16/ 81

0.0%

20/ 47

0.0%

20/ 47

Terminal-Bench 2.0

0.0%

25/ 32

0.0%

25/ 32

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.