Benchmark
HealthBench
What is 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…
- Released
- 2025-05-12
- Modality
- text
- Evaluates
- healthcare
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 9
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/healthbench?top_n=500
HealthBench results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT OSS 120B | OpenAI | 0.576 | 2025-08-05 | evidence |
| GPT OSS 20B | OpenAI | 0.425 | 2025-08-05 | evidence |
| GPT-5.3 Chat | OpenAI | 0.541 | 2026-03-04 | evidence |
| GPT-5.5 Instant | OpenAI | 0.514 | 2026-05-05 | evidence |
| GPT-5.6 Luna | OpenAI | 0.558 | 2026-07-09 | evidence |
| GPT-5.6 Sol | OpenAI | 0.57 | 2026-07-09 | evidence |
| GPT-5.6 Terra | OpenAI | 0.57 | 2026-07-09 | evidence |
| Kimi K2-Thinking-0905 | Moonshot AI | 0.58 | 2025-09-05 | evidence |
| Qwen3.8 Max | Qwen | 0.602 | 2026-08-02 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.