Knowledge · Benchmark profile
An open benchmark for clinician-facing model responses across care consult, writing and documentation, and medical research tasks.
Data verified 27 Jul 2026 · Methodology 1.8.0
Benchmark score on HealthBench Professional
GPT-5.6 Sol leads at 60.5%, followed by Claude Opus 5 (59.8%) and Muse Spark 1.1 (59.3%).
6 ranked models · higher is better · labels show rank and score
| Model | Rank | Provider | Score |
|---|---|---|---|
| GPT-5.6 Sol | #1 | OpenAI | 60.5% |
| Claude Opus 5 | #2 | Anthropic | 59.8% |
| Muse Spark 1.1 | #3 | Meta | 59.3% |
| GPT-5.6 Terra | #4 | OpenAI | 57.7% |
| GPT-5.6 Luna | #5 | OpenAI | 55.7% |
| GPT-5.4 | #6 | OpenAI | 48.1% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | GPT-5.6 Sol gpt-5.6-sol | OpenAI | closed | Reference only | 60.5% |
| #2 | Claude Opus 5 claude-opus-5 | Anthropic | closed | Reference only | 59.8% |
| #3 | Muse Spark 1.1 muse-spark-1-1 | Meta | closed | Reference only | 59.3% |
| #4 | GPT-5.6 Terra gpt-5.6-terra | OpenAI | closed | Estimated reference | 57.7% |
| #5 | GPT-5.6 Luna gpt-5.6-luna | OpenAI | closed | Estimated reference | 55.7% |
| #6 | GPT-5.4 gpt-5.4 | OpenAI | closed | Reference only | 48.1% |
The top of this snapshot is led by GPT-5.6 Sol at 60.5%; third place is 1.2 points behind. The top-6 spread is 12.4 points.
About HealthBench Professional
An open benchmark for clinician-facing model responses across care consult, writing and documentation, and medical research tasks. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
An open benchmark for clinician-facing model responses across care consult, writing and documentation, and medical research tasks.
GPT-5.6 Sol by OpenAI currently leads with 60.5%.
6 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
2026 · 21 results · Reference
Artificial Analysis MMLU-Pro2026 · 8 results · Reference
Massive Multitask Language Understanding2020 · 16 results · Reference
Graduate-Level Google-Proof Q&A2023 · 140 results · Reference
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines2025 · 38 results · Reference
Massive Multitask Language Understanding Professional2024 · 85 results · Reference
