GPT-6 Luna
- Made by
- OpenAI
- Released
- 22 September 2026
- Licence
- proprietary
- Context
- 1.05M
- Input, per 1M tokens
- $0.1
- Output, per 1M tokens
- $0.5
How this score is made
- HealthBench Professional0.60860.8 out of 100runs −2.5 hardadjusted 63.3weight 0.446, supportingsystem cardReported by the maker.OpenAI; length-adjusted; maximum reasoning effort; 60.8 (61.2, 2119) (adjusted, raw, mean response characters)
- HealthBench54.554.5 out of 100runs −0.5 leveladjusted 55.0weight 0.798, coresystem cardReported by the maker.OpenAI; length-adjusted; maximum reasoning effort; 54.5 (50.0, 1255) (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
- 58.0
- Field average, counts for 42.9% with 2 of 4 benchmarks
- 55.3
- Index
- = 56.8
Benchmark by benchmark
HealthBench Professional5 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
- 0.621Claude Fable 5.1
37 modelsFull benchmark
HealthBench22 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
- 56.3GPT-6 Luna (Anthropic run)
26 modelsFull benchmark
Artificial Analysis Healthcare & Medical Index20 of 29
- 61Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
- 58Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
- 53Claude Opus 5 (Adaptive Reasoning, Max Effort)
- 52Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
- 52GPT-6 Astra (max)
- 50Muse Spark 1.3 (max)
- 47GLM-5.3 (max)
- 47Grok 4.7 (xhigh)
- 45GLM 5.3 Flash
- 37GPT-6 Luna (max)
29 modelsFull benchmark