List your company
ResearchFormerly WizWand

Visual Mathematical Reasoning on WeMath strict

44.8AccuracyAdaVaR-7B
16.61623.93331.2538.567Sep 26, 2025
Updated 6mo ago

Evaluation results

MethodLinks
AdaVaR-7BCategory=Reasoning Models, Base Model=Qwen2.5-VL-7B, Parameter Size=7B, Reasoning Mode=Adaptive2025.0944.855.82
OVR-7BCategory=Reasoning Models, Base Model=Qwen2.5-VL-7B, Parameter Size=7B, Reasoning Mode=Text-based2025.0944.655.76
GPT-4oCategory=SFT & Close-source Models2025.0942.953.2
VLAA-Thinker-7BCategory=Reasoning Models, Base Model=Qwen2.5-VL-7B, Parameter Size=7B, Reasoning Mode=Text-based2025.0941.554.2
InternVL3-8BCategory=SFT & Close-source Models, Parameter Size=8B2025.0937.5—
MM-EurekaCategory=Reasoning Models, Base Model=Qwen2.5-VL-7B, Parameter Size=7B2025.0936.952.52
ViGoRL-7BCategory=Reasoning Models, Base Model=Qwen2.5-VL-7B, Parameter Size=7B2025.0936.350.53
VLAA-Thinker-3BCategory=Reasoning Models, Base Model=Qwen2.5-VL-3B, Parameter Size=3B, Reasoning Mode=Text-based2025.0933.846.7
AdaVaR-3BCategory=Reasoning Models, Base Model=Qwen2.5-VL-3B, Parameter Size=3B, Reasoning Mode=Adaptive2025.0933.850.84
Chain-of-FocusCategory=Reasoning Models, Base Model=Qwen2.5-VL-7B, Parameter Size=7B2025.0933.150.94
DeepEyesCategory=Reasoning Models, Base Model=Qwen2.5-VL-7B, Parameter Size=7B, Reasoning Mode=Visually-grounded2025.0932.753.72
Orsta-7BCategory=Reasoning Models, Base Model=Qwen2.5-VL-7B, Parameter Size=7B2025.0931.852.04
Qwen2.5-VL-7BCategory=Reasoning Models, Base Model=Qwen2.5-VL-7B, Parameter Size=7B2025.0931.250.9
LMM-R1Category=Reasoning Models, Base Model=Qwen2.5-VL-3B, Parameter Size=3B2025.0929.248.8
GRIT-3BCategory=Reasoning Models, Base Model=Qwen2.5-VL-3B, Parameter Size=3B2025.0929.145.8
ViGoRL-3BCategory=Reasoning Models, Base Model=Qwen2.5-VL-3B, Parameter Size=3B2025.0928.545.7
Qwen2.5-VL-3BCategory=Reasoning Models, Base Model=Qwen2.5-VL-3B, Parameter Size=3B2025.0921.245.74
LLaVA-OV-7BCategory=SFT & Close-source Models, Parameter Size=7B2025.0917.7—