Success Rate on Mini-ARC
52.03Success Rateo1 (Standard One-Stage)
Evaluation Results
| Method | Links | |
|---|---|---|
| o1 (Standard One-Stage)Pipeline=One-stage, Model=o12025.12 | 52.03 | |
| Claude-Sonnet-4.5 (Standard One-Stage)Pipeline=One-stage, Model=Claude-Sonnet-4.52025.12 | 34.22 | |
| Two-stage pipeline (Claude-Sonnet-4.5 + GPT-4o)Pipeline=Two-stage, Perception=Claude-Sonnet-4.5, Reasoning=GPT-4o2025.12 | 32.89 | |
| Two-stage pipeline (o1 + GPT-4o)Pipeline=Two-stage, Perception=o1, Reasoning=GPT-4o2025.12 | 31.54 | |
| Two-stage pipeline (GPT-4o + GPT-4o)Pipeline=Two-stage, Perception=GPT-4o, Reasoning=GPT-4o2025.12 | 20.13 | |
| GPT-4o (Standard One-Stage)Pipeline=One-stage, Model=GPT-4o2025.12 | 8.05 |