Wafer Defect Analysis on Wafer Defect Analysis
7.149Overall ScoreGemini-3-Flash
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Gemini-3-Flash2026.04 | 7.149 | 7.086 | 7.028 | 7.333 | |
| Qwen3-4B-RLModel Size=4B, Training Protocol=RL2026.04 | 6.493 | 6.377 | 6.559 | 6.543 | |
| Qwen3-4B-SFTModel Size=4B, Training Protocol=SFT2026.04 | 6.484 | 6.503 | 6.346 | 6.602 | |
| Qwen3-8B-RLModel Size=8B, Training Protocol=RL2026.04 | 6.388 | 6.438 | 6.377 | 6.349 | |
| Qwen3-8B-SFTModel Size=8B, Training Protocol=SFT2026.04 | 6.309 | 6.302 | 6.599 | 6.025 | |
| Qwen3.5-plus2026.04 | 6.224 | 6.488 | 6.006 | 6.179 | |
| Gemini-3.1-pro-preview2026.04 | 6.103 | 6.21 | 6.228 | 5.87 | |
| Qwen3.5-35B-A3BModel Size=35B-A3B2026.04 | 5.883 | 5.824 | 5.685 | 6.139 | |
| Qwen3.5-122B-A10BModel Size=122B-A10B2026.04 | 5.79 | 6.083 | 5.846 | 5.441 | |
| gpt5-mini2026.04 | 5.79 | 5.747 | 6.046 | 5.577 | |
| Qwen3.5-397B-A17BModel Size=397B-A17B2026.04 | 5.703 | 5.645 | 6.003 | 5.46 | |
| Qwen3-32BModel Size=32B2026.04 | 5.511 | 5.79 | 5.568 | 5.176 | |
| Qwen3-235B-A22BModel Size=235B-A22B2026.04 | 5.106 | 5.068 | 5.08 | 5.17 | |
| Gemma-3-27BModel Size=27B2026.04 | 4.918 | 4.83 | 4.833 | 5.09 | |
| GLM-4.6V2026.04 | 4.75 | 4.623 | 4.617 | 5.009 | |
| Kimi-k2.52026.04 | 4.705 | 4.738 | 4.735 | 4.642 | |
| seed-1.62026.04 | 4.587 | 4.414 | 4.747 | 4.602 | |
| Qwen3-8BModel Size=8B2026.04 | 4.534 | 4.747 | 4.367 | 4.488 | |
| Gemma-3-12BModel Size=12B2026.04 | 4.253 | 4.577 | 3.88 | 4.302 | |
| Qwen3-30B-A3BModel Size=30B-A3B2026.04 | 4.063 | 4.077 | 3.985 | 4.127 | |
| Qwen3-4BModel Size=4B2026.04 | 3.78 | 3.957 | 3.565 | 3.818 |