Models

Release date

Models

Claude Opus 4.6 (Thinking)

Release Date: 2/5/2026

Benchmarked by Vals Logo

Avg. Accuracy

71.73%

Latency

576.68s

Cost (In/Out)

5 / 25

Context Window

200k

Max Output Tokens

128k

Input Modality

Hyperparameter settings

Default Provider : Anthropic

Temperature

1

Top P

Default

Top K

Default

Max Output Tokens

128,000

Compute Effort

max

Benchmarks

Accuracy

Rankings

0.0%

1/ 26

0.0%

1/ 26

Vals Multimodal Index

0.0%

1/ 17

0.0%

1/ 17

0.0%

22/ 61

0.0%

22/ 61

0.0%

3/ 80

0.0%

3/ 80

Finance Agent (v1.1)

0.0%

1/ 28

0.0%

1/ 28

0.0%

6/ 58

0.0%

6/ 58

0.0%

1/ 14

0.0%

1/ 14

0.0%

3/ 37

0.0%

3/ 37

0.0%

1/ 89

0.0%

1/ 89

Vibe Code Bench

0.0%

2/ 16

0.0%

2/ 16

0.0%

4/ 80

0.0%

4/ 80

0.0%

3/ 83

0.0%

3/ 83

0.0%

9/ 88

0.0%

9/ 88

0.0%

5/ 102

0.0%

5/ 102

0.0%

10/ 88

0.0%

10/ 88

0.0%

2/ 82

0.0%

2/ 82

0.0%

5/ 55

0.0%

5/ 55

0.0%

1/ 48

0.0%

1/ 48

Terminal-Bench 2.0

0.0%

2/ 33

0.0%

2/ 33

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.