Feasibility Prediction on Warehouse
42F1@1Gemini 3.1 Pro Preview
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Gemini 3.1 Pro Preview2026.05 | 42 | 67 | 62.8 | |
| Qwen3 235B2026.05 | 41 | 60.8 | 56 | |
| GPT-5.2 Instant2026.05 | 35 | 63.4 | 56.9 | |
| Claude Opus 4.72026.05 | 33.3 | 63.2 | 55.7 | |
| Claude Sonnet 4.62026.05 | 33.3 | 64.9 | 59 |