GPT-5
- Made by
- OpenAI
- Released
- 7 August 2025
- Licence
- proprietary
- Context
- 400K
- Input, per 1M tokens
- $1.25
- Output, per 1M tokens
- $10
How this score is made
- HealthBench Professional0.46246.2 out of 100runs −2.5 hardadjusted 48.7weight 0.446, supportingsystem cardReported by the maker.length-adjusted, max reasoning effort, GPT-5.6 system card Table 6 column GPT-5 (51.0 unadjusted, 3616 chars)
- HealthBench57.757.7 out of 100runs −0.5 leveladjusted 58.2weight 0.798, coresystem cardReported by the maker.OpenAI; length-adjusted; maximum reasoning effort; 57.7 (63.1, 2904) (adjusted, raw, mean response characters)
- Health Optimization Bench: incretinNo result here, and none is filled in.
- SAFE-TeenNo result here, and none is filled in.
- Adjusted average of 2 benchmarks, by weight
- 54.8
- Field average, counts for 42.9% with 2 of 4 benchmarks
- 55.3
- Index
- = 55.0
Benchmark by benchmark
HealthBench Professional36 of 37
- 0.703GPT-6 Astra (Anthropic run)
- 0.692Claude Sonnet 5.5
- 0.660Claude Fable 5
- 0.656Claude Opus 5.5
- 0.655GPT-6 Luna (Anthropic run)
- 0.648Claude Haiku 5.5
- 0.642GPT-6.1 Sol
- 0.627GPT-6.1 Terra
- 0.623Muse Wonder Full
- 0.462GPT-5
37 modelsFull benchmark
HealthBench16 of 26
- 68.1Claude Opus 5.5
- 67.1Claude Opus 5
- 65.4Claude Sonnet 5.5
- 65.1Baichuan-M3
- 63.3GPT-5.2-High
- 62.7Claude Fable 5
- 61.6Claude Haiku 5.5
- 60Claude Fable 5.1
- 59.3Claude Opus 4.8
- 57.7GPT-5
26 modelsFull benchmark