List your company

Visual Reasoning on MMMU Pro Vision

51.9AccuracyGPT4-o
18.6227.2635.944.54Jan 1, 2026

Evaluation results

MethodLinks
GPT4-oSampling Strategy=avg@8, Inference Temperature=12026.0151.9
Gemini-2.0-FlashSampling Strategy=avg@8, Inference Temperature=12026.0151.7
CPPOBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0139
Vision-SR1Backbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0138.9
PAPOBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0138.7
NoisyRolloutBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0138.5
PerceptionR1Backbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0138.1
GRPOBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0137.9
OpenVLThinkerBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0135.5
Vision-MattersBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0135.5
Look-BackBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0134.5
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0133.7
CPPOBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0128.5
Visionary-R1Backbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0127.9
PAPOBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0126.8
GRPOBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0125.8
OpenVLThinkerBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0125
Qwen2.5-VL-3BBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0119.9