Models

Release date

Models

Compare Model

Release Date: 8/7/2025

Benchmarked by Vals Logo

Accuracy (Vals Index)

51.88% ± 1.98

Latency (Vals Index)

403.32s

Cost/Test (Vals Index)

$0.07

Context Window

400k

Max Output Tokens

128k

Input Modality

Hyperparameter settings

Default Provider : OpenAI

Temperature

Default

Top P

Default

Top K

Default

Max Output Tokens

128,000

Reasoning Effort

high

Benchmarks

Accuracy

Rankings

0.0%

± 1.98

23/ 34

0.0%

± 1.98

23/ 34

Vals Multimodal Index

0.0%

± 1.54

18/ 25

0.0%

± 1.54

18/ 25

0.0%

± 1.13

3/ 41

0.0%

± 1.13

3/ 41

0.0%

± 0.96

36/ 92

0.0%

± 0.96

36/ 92

Finance Agent (v1.1)

0.0%

± 2.90

17/ 40

0.0%

± 2.90

17/ 40

0.0%

± 2.05

16/ 47

0.0%

± 2.05

16/ 47

0.0%

± 1.92

15/ 47

0.0%

± 1.92

15/ 47

0.0%

± 0.92

14/ 66

0.0%

± 0.92

14/ 66

0.0%

± 2.88

15/ 22

0.0%

± 2.88

15/ 22

0.0%

± 3.34

17/ 46

0.0%

± 3.34

17/ 46

0.0%

± 0.85

6/ 100

0.0%

± 0.85

6/ 100

Vibe Code Bench

0.0%

± 3.54

17/ 22

0.0%

± 3.54

17/ 22

0.0%

± 0.84

20/ 92

0.0%

± 0.84

20/ 92

0.0%

± 2.00

28/ 95

0.0%

± 2.00

28/ 95

0.0%

± 3.32

28/ 50

0.0%

± 3.32

28/ 50

0.0%

± 0.98

4/ 101

0.0%

± 0.98

4/ 101

0.0%

± 0.45

38/ 113

0.0%

± 0.45

38/ 113

0.0%

± 0.18

7/ 95

0.0%

± 0.18

7/ 95

0.0%

± 0.37

39/ 93

0.0%

± 0.37

39/ 93

0.0%

± 0.98

22/ 63

0.0%

± 0.98

22/ 63

0.0%

± 2.19

29/ 37

0.0%

± 2.19

29/ 37

Terminal-Bench 2.0

0.0%

± 4.73

31/ 46

0.0%

± 4.73

31/ 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.