Kernel Generation on KernelBench Level 2 (Medium)
100Correlation CoefficientClaude-4.6-opus
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Claude-4.6-opusFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 100 | 99 | 5.83 | |
| Kernel-Smith-235B-RLFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 98 | 93 | 7.77 | |
| Qwen3-235B-2507-thinkFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 96 | 86 | 3.96 | |
| DeepSeek-v3.2-SpecialeFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 96 | 88 | 6.89 | |
| Gemini-3.0-proFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 96 | 95 | 4.78 | |
| Minimax-M2.5Framework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 91 | 77 | 1.06 | |
| Qwen3.5-397B-thinkFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 90 | 72 | 3.86 | |
| Kimi-K2.5Framework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 90 | 72 | 3.86 |