Models

Release date

Models

Compare Model

Release Date: 1/26/2026

Benchmarked by Vals Logo

Avg. Accuracy

67.43%

Latency

452.66s

Cost (In/Out)

0.6 / 3

Context Window

262k

Max Output Tokens

128k

Input Modality

Hyperparameter settings

Default Provider : Moonshot AI

Temperature

1

Top P

0.95

Top K

Default

Max Output Tokens

128,000

Show rankings only among open weight models

Benchmarks

Accuracy

Rankings

0.0%

8/ 28

0.0%

8/ 28

Vals Multimodal Index

0.0%

6/ 17

0.0%

6/ 17

0.0%

17/ 63

0.0%

17/ 63

0.0%

1/ 82

0.0%

1/ 82

Finance Agent (v1.1)

0.0%

12/ 30

0.0%

12/ 30

0.0%

12/ 58

0.0%

12/ 58

0.0%

4/ 37

0.0%

4/ 37

0.0%

14/ 91

0.0%

14/ 91

0.0%

5/ 82

0.0%

5/ 82

0.0%

13/ 85

0.0%

13/ 85

0.0%

12/ 43

0.0%

12/ 43

0.0%

11/ 90

0.0%

11/ 90

0.0%

13/ 90

0.0%

13/ 90

0.0%

14/ 84

0.0%

14/ 84

0.0%

4/ 55

0.0%

4/ 55

0.0%

14/ 50

0.0%

14/ 50

Terminal-Bench 2.0

0.0%

11/ 35

0.0%

11/ 35

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.