Kernel Generation on KernelBench Level 1 (Easy)
100AccuracyClaude-4.6-opus
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Claude-4.6-opusFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 100 | 70 | 2.14 | |
| Gemini-3.0-proFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 99 | 78 | 2.46 | |
| DeepSeek-v3.2-SpecialeFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 98 | 63 | 2.3 | |
| Kernel-Smith-235B-RLFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 97 | 70 | 2.3 | |
| Qwen3-235B-2507-thinkFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 92 | 57 | 1.86 | |
| Qwen3.5-397B-thinkFramework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 89 | 55 | 2 | |
| Kimi-K2.5Framework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 89 | 55 | 2 | |
| Minimax-M2.5Framework=Kernel-Smith evolution-agent, Evolution Rounds=402026.03 | 70 | 49 | 2.39 |