Causal Discovery on PROCAUEVAL Deprivation 1.0
50.3R-AvgInternVL-3.5
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| InternVL-3.5Size=8B, Category=Standard Models2026.05 | 50.3 | 28.8 | 51.2 | |
| Qwen3-VL-ThinkingSize=8B, Category=Thinking Models2026.05 | 50.2 | 8.8 | 79.3 | |
| Qwen3-VL-ThinkingSize=32B, Category=Larger Models2026.05 | 49.3 | 22 | 65 | |
| Keye-1.5Size=8B, Category=Thinking Models2026.05 | 49.2 | 12 | 73.3 | |
| GLM-4.1V-ThinkingSize=8B, Category=Thinking Models2026.05 | 43.9 | 18.2 | 69.1 | |
| InternVL-3.5Size=38B, Category=Larger Models2026.05 | 43.1 | 10.4 | 59.3 | |
| GPT-5.1-ThinkingSize=-, Category=Thinking Models2026.05 | 39.9 | 11.4 | 75.2 | |
| Qwen3-VLSize=32B, Category=Larger Models2026.05 | 39.3 | 17.2 | 62.1 | |
| MiMo-VL-RLSize=7B, Category=Thinking Models2026.05 | 38.3 | 17 | 56.1 | |
| Qwen3-VLSize=8B, Category=Standard Models2026.05 | 36.7 | 24.6 | 52.5 | |
| MiMo-VL-SFTSize=7B, Category=Standard Models2026.05 | 35.8 | 17.6 | 47.4 | |
| Video-R1Size=7B, Category=Thinking Models2026.05 | 32.8 | 26.2 | 45.6 | |
| VideoChat-R1.5Size=7B, Category=Thinking Models2026.05 | 30.3 | 19.2 | 50.4 | |
| GPT-5.1Size=-, Category=Standard Models2026.05 | 29.3 | 23.4 | 43.4 | |
| OneThinkerSize=8B, Category=Thinking Models2026.05 | 28.3 | 20.4 | 46.9 | |
| LongVILA-R1Size=7B, Category=Thinking Models2026.05 | 25.3 | 11.8 | 46 | |
| LLaVA-OneVisionSize=7B, Category=Standard Models2026.05 | 23.8 | 34.4 | 33.8 |