Models

Release date

Models

Compare Model

Release Date: 9/23/2025

Benchmarked by Vals Logo

Accuracy (Average)

62.83%

Latency (Average)

303.12s

Avg. 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

0.0%

± 0.47

40/ 41

0.0%

± 0.47

40/ 41

0.0%

± 0.98

53/ 92

0.0%

± 0.98

53/ 92

Finance Agent (v1.1)

0.0%

± 2.81

28/ 40

0.0%

± 2.81

28/ 40

0.0%

± 0.86

22/ 100

0.0%

± 0.86

22/ 100

0.0%

± 1.10

42/ 92

0.0%

± 1.10

42/ 92

0.0%

± 2.03

32/ 95

0.0%

± 2.03

32/ 95

0.0%

± 6.35

17/ 50

0.0%

± 6.35

17/ 50

0.0%

± 1.11

38/ 101

0.0%

± 1.11

38/ 101

0.0%

± 0.40

37/ 113

0.0%

± 0.40

37/ 113

0.0%

± 0.30

58/ 95

0.0%

± 0.30

58/ 95

0.0%

± 0.36

26/ 93

0.0%

± 0.36

26/ 93

Terminal-Bench 2.0

0.0%

± 4.60

36/ 46

0.0%

± 4.60

36/ 46

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.