OpenAI GPT-5.6 Launch - KernelGen 1P: leaderboard
KernelGen 1P row of the self-improvement table in OpenAI's GPT-5.6 launch post (2026-07-09), an OpenAI first-party kernel-generation evaluation whose tasks and grading are not published. Score in percent, higher is better; GPT-5.6 Sol, Terra, Luna and GPT-5.5 only.
Metric: Score (%). Source: openai.com. Source: deploymentsafety.openai.com. Saturation forecast: Around April 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 66.72 | #6 |
| 2 | GPT-5.6 Sol | 61.1 | #22 |
| 3 | GPT-6.1 Sol | 60.44 | #7 |
| 4 | GPT-5.6 Terra | 49.2 | #40 |
| 5 | GPT-6.1 Terra | 45.34 | #15 |
| 6 | GPT-6 Sol | 38.12 | #19 |
| 7 | GPT-5.5 | 29.3 | #33 |
| 8 | GPT-5.6 Luna | 22.4 | #79 |
No result here: #3 Claude Opus 5.5, #9 Gemini 4 Argon, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-6-launch-kernelgen-1p · How It Works · Data refreshed daily, snapshot 2026-11-05.