GPT-5.6 Terra
- Made by
- OpenAI
- Released
- 9 July 2026
- Licence
- proprietary
- Context
- 1.05M
- Input, per 1M tokens
- $2
- Output, per 1M tokens
- $12
How this score is made
- HealthBench Professional0.57757.7 out of 100runs −2.5 hardadjusted 60.2weight 0.446, supportingsystem cardReported by the maker.length-adjusted, max reasoning effort (62.4 unadjusted, 3,618 mean response chars); GPT-5.6 system card Table 6, column GPT-5.6-TERRA.
- HealthBench57.057.0 out of 100runs −0.5 leveladjusted 57.5weight 0.798, coresystem cardReported by the maker.length-adjusted (58.7 unadjusted), max reasoning effort
- 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
- 58.5
- Field average, counts for 42.9% with 2 of 4 benchmarks
- 55.3
- Index
- = 57.1
Benchmark by benchmark
HealthBench Professional20 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
- 0.577GPT-5.6 Terra
37 modelsFull benchmark
HealthBench18 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
- 57.0GPT-5.6 Terra
26 modelsFull benchmark
Artificial Analysis Healthcare & Medical Index19 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
- 39GPT-5.6 Terra (max)
29 modelsFull benchmark