Robotic Failure Analysis VQA on ViFailback-Bench
44.54AccuracyGemini-2.5-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-2.5-ProModel Category=General Closed-Source Models2025.12 | 44.54 | |
| GPT-4oModel Category=General Closed-Source Models2025.12 | 44.47 | |
| Qwen2.5-VL-72B-InstructModel Category=General Open-Source Models2025.12 | 44.21 | |
| Qwen3-VL-32B-InstructModel Category=General Open-Source Models2025.12 | 42.07 | |
| RoboBrain2.0-32BModel Category=Embodied Models2025.12 | 40.5 | |
| Qwen2.5-VL-32B-InstructModel Category=General Open-Source Models2025.12 | 40.02 | |
| Qwen3-VL-4B-InstructModel Category=General Open-Source Models2025.12 | 37.59 | |
| InternVL3-78BModel Category=General Open-Source Models2025.12 | 37.33 | |
| Qwen3-VL-8B-InstructModel Category=General Open-Source Models2025.12 | 35.92 | |
| Cosmos-Reason1-7BModel Category=Embodied Models2025.12 | 33.75 | |
| InternVL3-8BModel Category=General Open-Source Models2025.12 | 33.45 | |
| Qwen2.5-VL-7B-InstructModel Category=General Open-Source Models2025.12 | 31.87 | |
| RoboBrain2.0-3BModel Category=Embodied Models2025.12 | 31.65 | |
| RoboBrain2.0-7BModel Category=Embodied Models2025.12 | 30.84 | |
| Qwen2.5-VL-3B-InstructModel Category=General Open-Source Models2025.12 | 30.81 | |
| Qwen3-VL-2B-InstructModel Category=General Open-Source Models2025.12 | 28.39 |