Correspondence-Pointing on CrossPoint-Bench
95.87Object AccuracyHuman
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Human2025.12 | 95.87 | 91.18 | 93.63 | |
| CroPond-3BParameters=3B2025.12 | 84.3 | 62.44 | 73.87 | |
| CroPond-7BParameters=7B2025.12 | 83.88 | 71.49 | 77.97 | |
| Qwen3-VL-235B-A22B-ThinkingParameters=235B, MoE=A22B, Mode=Thinking2025.12 | 50.83 | 26.7 | 39.31 | |
| Qwen3-VL-30B-A3B-ThinkingParameters=30B, MoE=A3B, Mode=Thinking2025.12 | 32.23 | 19 | 25.92 | |
| Qwen2.5-VL-72B-InstructParameters=72B, Mode=Instruct2025.12 | 23.14 | 10.86 | 17.28 | |
| Gemini-2.5-Pro2025.12 | 20.25 | 12.22 | 16.41 | |
| Qwen2.5-VL-32B-InstructParameters=32B, Mode=Instruct2025.12 | 19.83 | 5.88 | 13.17 | |
| o32025.12 | 10.74 | 9.5 | 10.15 | |
| Qwen3-VL-235B-A22B-InstructParameters=235B, MoE=A22B, Mode=Instruct2025.12 | 7.85 | 4.98 | 6.48 | |
| Claude-Sonnet-42025.12 | 7.02 | 3.17 | 5.18 | |
| Qwen3-VL-30B-A3B-InstructParameters=30B, MoE=A3B, Mode=Instruct2025.12 | 4.55 | 3.62 | 4.1 | |
| Molmo-7B-DParameters=7B2025.12 | 4.13 | 1.81 | 3.02 | |
| Qwen2.5-VL-3B-InstructParameters=3B, Mode=Instruct2025.12 | 2.89 | 2.26 | 2.59 | |
| RoboRefer-8B-SFTParameters=8B, Mode=SFT2025.12 | 1.65 | 2.26 | 1.94 | |
| RoboPoint-v1-Vicuna-13BBackbone=Vicuna-13B2025.12 | 0.83 | 1.36 | 1.08 | |
| RoboBrain2.0-7BParameters=7B, reasoning_mode=no-thinking2025.12 | 0.41 | 1.36 | 0.86 | |
| RoboBrain2.0-7BParameters=7B, reasoning_mode=thinking2025.12 | 0.41 | 1.36 | 0.86 | |
| Qwen2.5-VL-7B-InstructParameters=7B, Mode=Instruct2025.12 | 0 | 0 | 0 |