Benchmark
HealthBench Consensus
What is HealthBench Consensus?
HealthBench Consensus is a HealthBench subset focused on questions where physician-created rubric criteria have especially high agreement, measuring healthcare…
- Released
- 2025-05-12
- Modality
- text
- Evaluates
- healthcare
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 4
Source provenance
HealthBench Consensus results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5.5 Instant | OpenAI | 0.947 | 2026-05-05 | evidence |
| GPT-5.6 Luna | OpenAI | 0.951 | 2026-07-09 | evidence |
| GPT-5.6 Sol | OpenAI | 0.955 | 2026-07-09 | evidence |
| GPT-5.6 Terra | OpenAI | 0.951 | 2026-07-09 | 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.