CodegenBench - BLAS x86-64: leaderboard
Metric: Pass@1 (%): share of problems whose first generated program compiles, runs and matches the reference output within tolerance; zero-shot through the official APIs with a short optimization system prompt, on the 106 BLAS subroutines (levels 1-3, several matrix shapes, strides and data types) compiled with gcc against OpenBLAS on a Xeon Platinum 8488C; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 74 |
| 2 | Claude Sonnet 4.6 | 70 |
| 3 | Claude Opus 4.6 | 67 |
| 4 | DeepSeek V4 Pro | 53 |
| 5 | DeepSeek V4 Flash | 48 |
| 6 | Qwen 3.6 Plus | 48 |
| 7 | Qwen 3.6 Flash | 40 |
| 8 | DeepSeek V3.2 | 35 |
| 9 | Qwen 3.5 Plus | 28 |
Interactive version: theaggregate.ai/benchmark?slug=codegenbench-blas-x86-64 · How It Works · Data refreshed daily, snapshot 2026-09-29.