List your company

Visual Tool-Use on V* Bench

88.2AccuracyMini-o3
64.2870.4976.782.91Dec 4, 2025

Evaluation results

MethodLinks
Mini-o3Source=Lai et al. (2025)2025.1288.2
ARM-Thinker-7BSize=7B, Backbone=Qwen2.5-VL-7B2025.1286.4
Pixel ReasonerSource=Lai et al. (2025)2025.1286.3
DeepEyesSource=Lai et al. (2025)2025.1283.3
Qwen3-VL-8BSize=8B2025.1282.2
Qwen2.5-VL-7BSize=7B2025.1275.4
InternVL3-8BSize=8B2025.1269.6
InternVL3.5-8BSize=8B2025.1269.1
GPT-4oSource=Lai et al. (2025)2025.1265.2