AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
HealthBench
An open-source benchmark for measuring performance and safety of large language models in healthcare, consisting of 5,000 multi-turn conversations evaluated by 262 physicians using 48,562 unique rubric criteria across health contexts and behavioral dimensions
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 9
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Qwen3.8 Max | 0.602 | Not recorded | Not recorded | 2026-08-02 · model_announcement | LLM Stats |
| Kimi K2-Thinking-0905 | 0.58 | Not recorded | Not recorded | 2025-09-05 · model_announcement | LLM Stats |
| GPT OSS 120B | 0.576 | Not recorded | Not recorded | 2025-08-05 · model_announcement | LLM Stats |
| GPT-5.6 Sol | 0.57 | Not recorded | Not recorded | 2026-07-09 · model_announcement | LLM Stats |
| GPT-5.6 Terra | 0.57 | Not recorded | Not recorded | 2026-07-09 · model_announcement | LLM Stats |
| GPT-5.6 Luna | 0.558 | Not recorded | Not recorded | 2026-07-09 · model_announcement | LLM Stats |
| GPT-5.3 Chat | 0.541 | Not recorded | Not recorded | 2026-03-04 · model_announcement | LLM Stats |
| GPT-5.5 Instant | 0.514 | Not recorded | Not recorded | 2026-05-05 · model_announcement | LLM Stats |
| GPT OSS 20B | 0.425 | Not recorded | Not recorded | 2025-08-05 · model_announcement | LLM Stats |