New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
HealthBench Hard benchmark
AI model leaderboard for the HealthBench Hard benchmark. Compare how large language models score on HealthBench Hard, see the full ranking, and understand what this AI benchmark measures. gpt-oss-120b currently leads with 30%. Hardest subset of HealthBench targeting challenging health conversations.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | gpt-oss-120b | OpenAI | 30% | high reasoning | official ↗ |
| #2 | gpt-oss-120b | OpenAI | 30% | high | official ↗ |
| #3 | gpt-oss-20b | OpenAI | 10.8% | high reasoning | official ↗ |
| #4 | gpt-oss-20b | OpenAI | 10.8% | high | official ↗ |
Frequently asked questions about HealthBench Hard
What is the HealthBench Hard benchmark?
Hardest subset of HealthBench targeting challenging health conversations.
How is the HealthBench Hard benchmark scored?
HealthBench Hard is scored using the score (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on HealthBench Hard?
As of the latest reported scores on GenAIList, gpt-oss-120b achieves the highest result on HealthBench Hard with a score of 30%.
Is a higher HealthBench Hard score better?
Yes. On HealthBench Hard a higher score indicates better performance, so models near the top of the leaderboard are the strongest.