HealthBench Hard (length-adjusted score)
Hard subset of OpenAI's medical conversation evaluation. Length-adjusted score.
- Category
- Knowledge
- Unit
- Score
- Higher is better
- Comparison groups
- 2total
- Currently available model rankings · Ranked results: 4
- All models (records): Groups: 2 · Entries: 7
Rankings
Values with different source types (official, third-party, paper) or measurement conditions cannot be compared, so rankings are separated by comparison group (the same source, or sources verified to use the same conditions).
Rankings include only models currently available in Claude Code / Codex, excluding legacy models.
official results (GPT-6 Astra System Card (Table 6. HealthBench Evaluations))
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | not stated | 36.6 | — | OpenAI | GPT-6 Astra System Card (Table 6. HealthBench Evaluations)Retrieved 2026-11-12 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted scoreSource excerpt36.6Location Table 6 "HealthBench Evaluations - reported as length-adjusted score", HealthBench Hard row |
official results (Addendum to GPT-6 Astra System Card: GPT-6.1 Terra)
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol | not stated | 36.2 | — | OpenAI | Addendum to GPT-6 Astra System Card: GPT-6.1 TerraRetrieved 2026-11-14 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted score. Parentheses contain the unadjusted score and mean response length in characters; only the leading value is used as score. Cost not stated.Source excerpt36.2 (33.4, 1646)Location §5.1 Table 5, HealthBench Hard length-adjusted row, gpt-6-1-sol column |
| 2 | GPT-6.1 Terra | not stated | 31.4 | — | OpenAI | Addendum to GPT-6 Astra System Card: GPT-6.1 TerraRetrieved 2026-11-14 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted score. Parentheses contain the unadjusted score and mean response length in characters; only the leading value is used as score. Cost not stated.Source excerpt31.4 (26.0, 1306)Location §5.1 Table 5, HealthBench Hard length-adjusted row, gpt-6-1-terra column |
| 2 | GPT-6 Luna | not stated | 31.4 | — | OpenAI | Addendum to GPT-6 Astra System Card: GPT-6.1 TerraRetrieved 2026-11-14 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted score. Parentheses contain the unadjusted score and mean response length in characters; only the leading value is used as score. Cost not stated.Source excerpt31.4 (25.4, 1241)Location §5.1 Table 5, HealthBench Hard length-adjusted row, gpt-6-luna column |
All model rankings (records)
These rankings are recalculated by comparison group including legacy models and models unavailable in Claude Code / Codex. They differ from the rankings above because the set of models differs.
Show rankings including legacy and unavailable models (entries: 7)
official results (GPT-6 Astra System Card (Table 6. HealthBench Evaluations))
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | not stated | 36.6 | — | OpenAI | GPT-6 Astra System Card (Table 6. HealthBench Evaluations)Retrieved 2026-11-12 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted scoreSource excerpt36.6Location Table 6 "HealthBench Evaluations - reported as length-adjusted score", HealthBench Hard row |
| 2 | GPT-5.6 Sol | not stated | 33.1 | — | OpenAI | GPT-6 Astra System Card (Table 6. HealthBench Evaluations)Retrieved 2026-11-12 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted scoreSource excerpt33.1Location Table 6 "HealthBench Evaluations - reported as length-adjusted score", HealthBench Hard row |
| 3 | GPT-5.6 Terra | not stated | 32.7 | — | OpenAI | GPT-6 Astra System Card (Table 6. HealthBench Evaluations)Retrieved 2026-11-12 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted scoreSource excerpt32.7Location Table 6 "HealthBench Evaluations - reported as length-adjusted score", HealthBench Hard row |
| 4 | GPT-5.6 Luna | not stated | 32 | — | OpenAI | GPT-6 Astra System Card (Table 6. HealthBench Evaluations)Retrieved 2026-11-12 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted scoreSource excerpt32.0Location Table 6 "HealthBench Evaluations - reported as length-adjusted score", HealthBench Hard row |
official results (Addendum to GPT-6 Astra System Card: GPT-6.1 Terra)
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | GPT-6.1 Sol | not stated | 36.2 | — | OpenAI | Addendum to GPT-6 Astra System Card: GPT-6.1 TerraRetrieved 2026-11-14 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted score. Parentheses contain the unadjusted score and mean response length in characters; only the leading value is used as score. Cost not stated.Source excerpt36.2 (33.4, 1646)Location §5.1 Table 5, HealthBench Hard length-adjusted row, gpt-6-1-sol column |
| 2 | GPT-6.1 Terra | not stated | 31.4 | — | OpenAI | Addendum to GPT-6 Astra System Card: GPT-6.1 TerraRetrieved 2026-11-14 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted score. Parentheses contain the unadjusted score and mean response length in characters; only the leading value is used as score. Cost not stated.Source excerpt31.4 (26.0, 1306)Location §5.1 Table 5, HealthBench Hard length-adjusted row, gpt-6-1-terra column |
| 2 | GPT-6 Luna | not stated | 31.4 | — | OpenAI | Addendum to GPT-6 Astra System Card: GPT-6.1 TerraRetrieved 2026-11-14 · Vendor-reported value. Self-reported by OpenAI. effort not stated. length-adjusted score. Parentheses contain the unadjusted score and mean response length in characters; only the leading value is used as score. Cost not stated.Source excerpt31.4 (25.4, 1241)Location §5.1 Table 5, HealthBench Hard length-adjusted row, gpt-6-luna column |