Causal Discovery on PROCAUEVAL Incongruence 1.0
51.2R-AvgKeye-1.5
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Keye-1.5Size=8B, Category=Thinking Models2026.05 | 51.2 | 14 | 78 | |
| Qwen3-VL-ThinkingSize=8B, Category=Thinking Models2026.05 | 50.1 | 8 | 79.3 | |
| Qwen3-VL-ThinkingSize=32B, Category=Larger Models2026.05 | 42.4 | 8.2 | 63.8 | |
| GPT-5.1-ThinkingSize=-, Category=Thinking Models2026.05 | 38.3 | 11 | 70.2 | |
| GLM-4.1V-ThinkingSize=8B, Category=Thinking Models2026.05 | 37.3 | 9.8 | 65.5 | |
| VideoChat-R1.5Size=7B, Category=Thinking Models2026.05 | 36.6 | 17.6 | 60.9 | |
| Qwen3-VLSize=32B, Category=Larger Models2026.05 | 35 | 13.4 | 68.6 | |
| MiMo-VL-RLSize=7B, Category=Thinking Models2026.05 | 34.1 | 10.2 | 52.4 | |
| MiMo-VL-SFTSize=7B, Category=Standard Models2026.05 | 33.2 | 6.8 | 63.2 | |
| OneThinkerSize=8B, Category=Thinking Models2026.05 | 33.1 | 4.2 | 50.9 | |
| InternVL-3.5Size=8B, Category=Standard Models2026.05 | 32.6 | 17 | 43.1 | |
| Video-R1Size=7B, Category=Thinking Models2026.05 | 31.6 | 16.4 | 52.4 | |
| Qwen3-VLSize=8B, Category=Standard Models2026.05 | 31.2 | 13.2 | 54.1 | |
| InternVL-3.5Size=38B, Category=Larger Models2026.05 | 29.4 | 17.4 | 58.2 | |
| LLaVA-OneVisionSize=7B, Category=Standard Models2026.05 | 20.6 | 28.2 | 53.3 | |
| GPT-5.1Size=-, Category=Standard Models2026.05 | 20.5 | 28.6 | 40.6 | |
| LongVILA-R1Size=7B, Category=Thinking Models2026.05 | 18.9 | 7.4 | 33.8 |