TestsBenchmarks · Knowledge
HealthBench Professional
Clinician-oriented HealthBench split; Anthropic and OpenAI use different scoring (not comparable across vendors).
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Claude Sonnet 5.5 | Anthropic | 69.2% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | — | 28 Sep 2026 |
| 2 | Claude Opus 5.5 | Anthropic | 65.6% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | — | 22 Sep 2026 |
| 3 | GPT-6 Astra | OpenAI | 63.4% | Defaultbest score across efforts (OpenAI table: "maximum at any effort") | Maker's own figureVendor-reportedOpenAI ↗ | — | 3 Sep 2026 |
| 4 | Claude Fable 5.1 | Anthropic | 62.1% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | — | 1 Sep 2026 |
| 5 | GPT-5.6 Sol | OpenAI | 60.5% | Defaultbest score across efforts (OpenAI table: "maximum at any effort") | Maker's own figureVendor-reportedOpenAI ↗ | — | 3 Sep 2026 |
| 6 | Claude Opus 5 | Anthropic | 59.8% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | — | 24 Jul 2026 |
| 7 | Claude Sonnet 5 | Anthropic | 57.8% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | — | 30 Jun 2026 |
| 8 | GPT-5.6 Terra | OpenAI | 57.7% | DefaultGPT-5.6 launch table (effort not stated; text cites max for headline results) | Maker's own figureVendor-reportedOpenAI ↗ | — | 9 Jul 2026 |
| 9 | Claude Opus 4.8 | Anthropic | 57.4% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | — | 24 Jul 2026 |
| 10 | Grok 4.7 | SpaceXAI (formerly xAI) | 56.7% | Extra high | Maker's own figureVendor-reportedSpaceXAI ↗ | — | 21 Sep 2026 |
| 11 | GPT-5.6 Luna | OpenAI | 55.7% | DefaultGPT-5.6 launch table (effort not stated; text cites max for headline results) | Maker's own figureVendor-reportedOpenAI ↗ | — | 9 Jul 2026 |
| 12 | GPT-5.5 | OpenAI | 49.5% | DefaultGPT-5.6 launch table (effort not stated; text cites max for headline results) | Maker's own figureVendor-reportedOpenAI ↗ | — | 9 Jul 2026 |
| 13 | Grok 4.6 | SpaceXAI (formerly xAI) | 48.5% | High | Maker's own figureVendor-reportedSpaceXAI ↗ | — | 21 Sep 2026 |
| 14 | Claude Sonnet 4.6 | Anthropic | 44.2% | Maxadaptive thinking, effort=max | Maker's own figureVendor-reportedAnthropic ↗ | — | 30 Jun 2026 |