LLM Stats (KernelGen 1P): leaderboard
OpenAI's KernelGen 1P evaluation, as tracked by LLM Stats: agents must write and optimize compute kernels for OpenAI first-party hardware within a benchmark harness and correctness and performance tests. Scored by mean rubric credit (%) for producing correct kernels that improve speed over a reference implementation, with missing scores counted as zero; higher is better. LLM Stats combines GPT-6.2 Astra and Sol scores from the GPT-6.2 system card (Table 5) with GPT-5.6 Sol, Terra and Luna scores from the GPT-5.6 launch post.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around February 2027. 5 models tracked. Updated 19 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.2 Astra | 76.92 | #4 |
| 2 | GPT-6.2 Sol | 74.71 | #12 |
| 3 | GPT-5.6 Sol | 61.1 | #36 |
| 4 | GPT-5.6 Terra | 49.2 | #72 |
| 5 | GPT-5.6 Luna | 22.4 | #133 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #5 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-kernelgen-1p · How It Works · Data refreshed daily, snapshot 2026-11-20.