Visual Tool-Use on V* Bench
88.2AccuracyMini-o3
Evaluation Results
| Method | Links | |
|---|---|---|
| Mini-o3Source=Lai et al. (2025)2025.12 | 88.2 | |
| ARM-Thinker-7BSize=7B, Backbone=Qwen2.5-VL-7B2025.12 | 86.4 | |
| Pixel ReasonerSource=Lai et al. (2025)2025.12 | 86.3 | |
| DeepEyesSource=Lai et al. (2025)2025.12 | 83.3 | |
| Qwen3-VL-8BSize=8B2025.12 | 82.2 | |
| Qwen2.5-VL-7BSize=7B2025.12 | 75.4 | |
| InternVL3-8BSize=8B2025.12 | 69.6 | |
| InternVL3.5-8BSize=8B2025.12 | 69.1 | |
| GPT-4oSource=Lai et al. (2025)2025.12 | 65.2 |