List your company
ResearchFormerly WizWand

General Visual Understanding on VisNumBench

44.6AccuracyVision-SR1
8.61617.95827.336.642Aug 27, 2025Oct 9, 2025Nov 21, 2025Jan 3, 2026Feb 15, 2026Mar 30, 2026May 13, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Vision-SR1Backbone=Mimo-VL-7B2025.0844.649.5
Vision-SR1Backbone=Qwen2.5-VL-7B2025.0843.552.2
Vision-R1Backbone=Qwen2.5-VL-7B, Training Data=47K data2025.084350.7
Vision-SR1Backbone=Qwen2.5-VL-3B2025.0841.948.8
GRPOBackbone=Qwen2.5-VL-7B2026.0541.5—
PDCRBackbone=Qwen2.5-VL-7B2026.0541.1—
PACRBackbone=Qwen2.5-VL-7B2026.0540.1—
DAPOBackbone=Qwen2.5-VL-7B2026.0540—
PDCRBackbone=Qwen3-VL-8B-Instruct2026.0537.6—
GRPOBackbone=Qwen3-VL-8B-Instruct2026.0537.2—
PACRBackbone=Qwen3-VL-8B-Instruct2026.0537.1—
DAPOBackbone=Qwen3-VL-8B-Instruct2026.0537—
Vision-R1Backbone=Qwen2.5-VL-3B, Training Data=47K data2025.0836.747.1
Vision-R1Backbone=Mimo-VL-7B, Training Data=47K data2025.0833.546
PDCRBackbone=Qwen2.5-VL-3B2026.0533.3—
Vision-R1 (7B)Backbone=7B2025.083344.5
Vision-R1Backbone=Vision-R1 (7B)2026.0533—
PACRBackbone=Qwen2.5-VL-3B2026.0532.9—
DAPOBackbone=Qwen2.5-VL-3B2026.0531.8—
Zero-shot InferenceBackbone=Mimo-VL-7B, Inference Protocol=Zero-shot (before RL)2025.0830.244.4
GRPOBackbone=Qwen2.5-VL-3B2026.0529.9—
Zero-shot InferenceBackbone=Qwen3-VL-8B-Instruct2026.0529.1—
Zero-shot InferenceBackbone=Qwen2.5-VL-7B, Inference Protocol=Zero-shot (before RL)2025.0821.441.5
Percention-R1 (7B)Backbone=7B2025.0815.945.2
Perception-R1Backbone=Perception-R1 (7B)2026.0515.9—
Zero-shot InferenceBackbone=Qwen2.5-VL-3B, Inference Protocol=Zero-shot (before RL)2025.0815.735.5
Zero-shot InferenceBackbone=Qwen2.5-VL-3B, Mode=Zero-shot2026.0515.4—
Zero-shot InferenceBackbone=Qwen2.5-VL-7B, Mode=Zero-shot2026.0512.6—
Visionary-R1 (3B)Backbone=3B2025.081033.9
Visionary-R1Backbone=Visionary-R1 (3B)2026.0510—