Feasibility Prediction on Search R1
40.2F1@1GPT-5.2 Instant
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-5.2 Instant2026.05 | 40.2 | 38.3 | 0 | |
| Claude Opus 4.72026.05 | 39.4 | 40.5 | 5.6 | |
| Claude Sonnet 4.62026.05 | 37.9 | 33.3 | 0 | |
| Qwen3 235B2026.05 | 33.2 | 23.9 | 30.9 | |
| Gemini 3.1 Pro Preview2026.05 | 24.5 | 24.8 | 0 |