Models

Release date

Models

Claude Sonnet 4.5 (Thinking)

Release Date: 9/29/2025

Benchmarked by Vals Logo

Anthropic's latest flagship model

Avg. Accuracy

66.4%

Latency

453.2s

Cost (In/Out)

3.00 / 15.00

Context Window

1M

Max Output Tokens

64k

Input Modality

Benchmarks

Accuracy

Rankings

Vibe Code Bench

0.0%

13/ 13

0.0%

13/ 13

0.0%

28/ 28

0.0%

28/ 28

0.0%

50/ 50

0.0%

50/ 50

0.0%

64/ 64

0.0%

64/ 64

0.0%

48/ 48

0.0%

48/ 48

0.0%

81/ 81

0.0%

81/ 81

0.0%

51/ 51

0.0%

51/ 51

0.0%

71/ 71

0.0%

71/ 71

0.0%

73/ 73

0.0%

73/ 73

0.0%

96/ 96

0.0%

96/ 96

0.0%

77/ 77

0.0%

77/ 77

0.0%

73/ 73

0.0%

73/ 73

0.0%

71/ 71

0.0%

71/ 71

0.0%

47/ 47

0.0%

47/ 47

0.0%

71/ 71

0.0%

71/ 71

0.0%

27/ 27

0.0%

27/ 27

0.0%

37/ 37

0.0%

37/ 37

0.0%

35/ 35

0.0%

35/ 35

0.0%

23/ 23

0.0%

23/ 23

Vals Multimodal Index

0.0%

15/ 15

0.0%

15/ 15

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.