OpenAI GPT-5.6 Launch - MedChemBench (Internal): leaderboard
OpenAI's internal medicinal-chemistry benchmark (MedChemBench), science and health table of OpenAI's GPT-5.6 launch post (2026-07-09). Score in percent, higher is better; only GPT-5.6 Sol, Terra, Luna and GPT-5.5 have values.
Metric: Score (%). Source: openai.com. Saturation forecast: Around September 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 48.3 | #22 |
| 2 | GPT-5.5 | 35.5 | #33 |
| 3 | GPT-5.6 Terra | 35 | #40 |
| 4 | GPT-5.6 Luna | 30.4 | #79 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-6-launch-medchembench-internal · How It Works · Data refreshed daily, snapshot 2026-11-05.