Fine-grained Grounding on CrossPoint-Bench
98.49Object AccuracyHuman
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Human2025.12 | 98.49 | 96.63 | 97.44 | |
| CroPond-7BParameters=7B2025.12 | 93.94 | 87.64 | 87.18 | |
| CroPond-3BParameters=3B2025.12 | 90.91 | 73.03 | 76.92 | |
| Human2025.12 | 83.57 | 76.37 | 79.51 | |
| Qwen3-VL-235B-A22B-InstructParameters=235B, MoE=A22B, Mode=Instruct2025.12 | 79.17 | 54.63 | 62.18 | |
| CroPond-3BParameters=3B2025.12 | 78.57 | 43.96 | 59.01 | |
| Qwen3-VL-235B-A22B-ThinkingParameters=235B, MoE=A22B, Mode=Thinking2025.12 | 77.08 | 61.11 | 66.03 | |
| Gemini-2.5-Pro2025.12 | 75 | 53.7 | 60.26 | |
| Qwen3-VL-235B-A22B-ThinkingParameters=235B, MoE=A22B, Mode=Thinking2025.12 | 74.29 | 58.24 | 65.22 | |
| Qwen3-VL-30B-A3B-ThinkingParameters=30B, MoE=A3B, Mode=Thinking2025.12 | 72.86 | 38.46 | 53.42 | |
| RoboBrain2.0-7BParameters=7B, reasoning_mode=thinking2025.12 | 72.86 | 40.66 | 54.66 | |
| CroPond-7BParameters=7B2025.12 | 71.43 | 51.65 | 60.25 | |
| o32025.12 | 70.83 | 60.19 | 63.46 | |
| Qwen3-VL-235B-A22B-InstructParameters=235B, MoE=A22B, Mode=Instruct2025.12 | 70 | 52.75 | 60.25 | |
| Qwen2.5-VL-3B-InstructParameters=3B, Mode=Instruct2025.12 | 67.14 | 41.76 | 52.8 | |
| Qwen2.5-VL-7B-InstructParameters=7B, Mode=Instruct2025.12 | 65.71 | 35.16 | 48.45 | |
| Qwen2.5-VL-72B-InstructParameters=72B, Mode=Instruct2025.12 | 65.71 | 46.15 | 54.66 | |
| RoboBrain2.0-7BParameters=7B, reasoning_mode=no-thinking2025.12 | 64.29 | 41.76 | 51.55 | |
| RoboRefer-8B-SFTParameters=8B, Mode=SFT2025.12 | 62.86 | 32.97 | 45.96 | |
| Molmo-7B-DParameters=7B2025.12 | 62.86 | 36.26 | 47.83 | |
| Qwen3-VL-30B-A3B-InstructParameters=30B, MoE=A3B, Mode=Instruct2025.12 | 55.71 | 26.37 | 39.13 | |
| Qwen2.5-VL-7B-InstructParameters=7B, Mode=Instruct2025.12 | 54.55 | 37.08 | 41.03 | |
| Gemini-2.5-Pro2025.12 | 50 | 19.78 | 32.92 | |
| Qwen3-VL-30B-A3B-InstructParameters=30B, MoE=A3B, Mode=Instruct2025.12 | 50 | 41.67 | 44.23 | |
| Qwen2.5-VL-32B-InstructParameters=32B, Mode=Instruct2025.12 | 47.92 | 40.74 | 42.95 | |
| Qwen2.5-VL-72B-InstructParameters=72B, Mode=Instruct2025.12 | 45.83 | 51.85 | 50 | |
| Qwen3-VL-30B-A3B-ThinkingParameters=30B, MoE=A3B, Mode=Thinking2025.12 | 45.83 | 45.37 | 45.51 | |
| Claude-Sonnet-42025.12 | 41.67 | 37.04 | 38.46 | |
| RoboBrain2.0-7BParameters=7B, reasoning_mode=no-thinking2025.12 | 39.58 | 33.33 | 35.26 | |
| RoboPoint-v1-Vicuna-13BBackbone=Vicuna-13B2025.12 | 37.5 | 25.93 | 29.49 | |
| Molmo-7B-DParameters=7B2025.12 | 37.5 | 35.19 | 35.9 | |
| Qwen2.5-VL-3B-InstructParameters=3B, Mode=Instruct2025.12 | 33.33 | 33.71 | 33.97 | |
| Qwen2.5-VL-32B-InstructParameters=32B, Mode=Instruct2025.12 | 32.86 | 14.29 | 22.36 | |
| RoboBrain2.0-7BParameters=7B, reasoning_mode=thinking2025.12 | 29.17 | 41.67 | 37.82 | |
| RoboRefer-8B-SFTParameters=8B, Mode=SFT2025.12 | 22.92 | 31.48 | 28.85 | |
| Claude-Sonnet-42025.12 | 17.14 | 7.69 | 11.8 | |
| o32025.12 | 11.43 | 6.59 | 8.7 | |
| RoboPoint-v1-Vicuna-13BBackbone=Vicuna-13B2025.12 | 7.14 | 7.69 | 7.45 |