Models

Release date

Models

Release Date: 8/7/2025

Benchmarked by Vals Logo

GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.

Avg. Accuracy

67.79%

Latency

504.52s

Cost (In/Out)

1.25 / 10

Context Window

400k

Max Output Tokens

128k

Input Modality

Benchmarks

Accuracy

Rankings

0.0%

31/ 31

0.0%

31/ 31

Vals Multimodal Index

0.0%

18/ 18

0.0%

18/ 18

0.0%

59/ 59

0.0%

59/ 59

0.0%

82/ 82

0.0%

82/ 82

0.0%

57/ 57

0.0%

57/ 57

0.0%

56/ 56

0.0%

56/ 56

0.0%

36/ 36

0.0%

36/ 36

0.0%

87/ 87

0.0%

87/ 87

Vibe Code Bench

0.0%

15/ 15

0.0%

15/ 15

0.0%

78/ 78

0.0%

78/ 78

0.0%

79/ 79

0.0%

79/ 79

0.0%

42/ 42

0.0%

42/ 42

0.0%

86/ 86

0.0%

86/ 86

0.0%

102/ 102

0.0%

102/ 102

0.0%

60/ 60

0.0%

60/ 60

0.0%

86/ 86

0.0%

86/ 86

0.0%

75/ 75

0.0%

75/ 75

0.0%

80/ 80

0.0%

80/ 80

0.0%

55/ 55

0.0%

55/ 55

0.0%

45/ 45

0.0%

45/ 45

0.0%

47/ 47

0.0%

47/ 47

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.