CUDABeaver - Pass@1: leaderboard
CUDABeaver (2026) gives a model a real failing CUDA kernel from an LLM generation run, its build and test commands and the raw error, and asks for a repair that stays correct without falling back to a slower program. This board is the percentage of the 213 tasks solved by the first repair attempt, counting a repair only if it runs at least 0.7 times as fast as the reference; higher is better.
Metric: Share of the 213 broken-start CUDA debugging tasks (%) whose first repair attempt compiles, passes the task tests and runs at least 0.7 times as fast as the reference (performance gate p=0.7), default protocol: category-aware error feedback (level L3), iterative sampling at temperature 0.7; higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 6 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 Plus | 15.5 | #245 |
| 2 | Gemma 4 31B (IT) | 14.7 | #354 |
| 3 | GPT-5.4 | 14.5 | #138 |
| 4 | Kimi K2.6 | 13.6 | #197 |
| 5 | Qwen 3.6 27B | 10.3 | #358 |
| 6 | GLM-4.7 | 7.5 | #383 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=cudabeaver-pass-1 · How It Works · Data refreshed daily, snapshot 2026-11-22.