List your company

Visual Question Answering on HRBench-4K (FSP/FCP/Overall)

92.8FSP ScoreConFoThinking (Qwen3-VL-8B)
64.40871.77979.1586.521Feb 26, 2026

Evaluation results

MethodLinks
ConFoThinking (Qwen3-VL-8B)Backbone=Qwen3-VL-8B2026.0292.867.380
ConFoThinking (Qwen2.5-VL-7B)Backbone=Qwen2.5-VL-7B2026.0291.856.874.3
Qwen3-VL-8BBackbone=Qwen3-VL-8B2026.0288.364.576.4
ConFoThinking (Qwen3-VL-4B)Backbone=Qwen3-VL-4B2026.0287.86877.9
Pixel-Reasoner2026.0286.361.874
Qwen3-VL-4BBackbone=Qwen3-VL-4B2026.028662.574.3
LLaVA-OneVision-1.5-8BBackbone=LLaVA-OneVision-1.5-8B2026.0285.858.272
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B2026.0285.352.368.8
InternVL3.5-8BBackbone=InternVL3.5-8B2026.0285.360.873.2
Qwen3-VL-8B (with tools)Backbone=Qwen3-VL-8B, Thinking Tools=true2026.028565.575.3
Qwen3-VL-4B (with tools)Backbone=Qwen3-VL-4B, Thinking Tools=true2026.0284.362.373.3
ZoomEye2026.0284.25569.6
Visual Sketchpad2026.0281.357.869.5
SEAL2026.0271.54960.3
ICoT2026.0265.55560.3