Models

Release date

Models

Claude Sonnet 4 (Thinking)

Release Date: 5/22/2025

Benchmarked by

Anthropic's latest-generation workhorse model, offering a balance of performance and speed.

Avg. Accuracy

66.8%

Latency

244.2s

Cost (In/Out)

3.00 / 15.00

Context Window

200k

Max Output Tokens

64k

Input Modality

Benchmarks

Accuracy

Rankings

0.0%

22/ 22

0.0%

22/ 22

0.0%

43/ 43

0.0%

43/ 43

0.0%

56/ 56

0.0%

56/ 56

0.0%

39/ 39

0.0%

39/ 39

0.0%

73/ 73

0.0%

73/ 73

0.0%

45/ 45

0.0%

45/ 45

0.0%

54/ 54

0.0%

54/ 54

0.0%

63/ 63

0.0%

63/ 63

0.0%

66/ 66

0.0%

66/ 66

0.0%

88/ 88

0.0%

88/ 88

0.0%

69/ 69

0.0%

69/ 69

0.0%

65/ 65

0.0%

65/ 65

0.0%

63/ 63

0.0%

63/ 63

0.0%

42/ 42

0.0%

42/ 42

0.0%

62/ 62

0.0%

62/ 62

0.0%

20/ 20

0.0%

20/ 20

0.0%

28/ 28

0.0%

28/ 28

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.