OpenAI GPT-5.6 Launch - GeneBench Pro: leaderboard
GeneBench Pro row of the science and health table in OpenAI's GPT-5.6 launch post (2026-07-09). Score in percent, higher is better; seven models including Claude Opus 4.8, Gemini 3.1 Pro Preview and Gemini 3.5 Flash. The GPT-6 Astra post used the later v13 (GPT-5.6 Sol 32.3 there vs 28.7 here), so each launch keeps its own board.
Metric: Score (%). Source: openai.com. Saturation forecast: Around January 2028. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 28.7 | #22 |
| 2 | GPT-5.6 Terra | 23.3 | #40 |
| 3 | Claude Opus 4.8 | 16 | #39 |
| 4 | GPT-5.5 | 12 | #33 |
| 5 | GPT-5.6 Luna | 10.8 | #79 |
| 6 | Gemini 3.5 Flash | 8.14 | #66 |
| 7 | Gemini 3.1 Pro (Preview) | 3.1 | #64 |
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-genebench-pro · How It Works · Data refreshed daily, snapshot 2026-11-05.