List your company

Mathematical Reasoning on MathVision MVisionm

41.3AccuracyGemini-2.0-Flash
18.62824.51430.436.286Jan 1, 2026

Evaluation results

MethodLinks
Gemini-2.0-FlashSampling Strategy=avg@8, Inference Temperature=12026.0141.3
GPT4-oSampling Strategy=avg@8, Inference Temperature=12026.0130.6
CPPOBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0129.9
NoisyRolloutBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0129.4
Vision-SR1Backbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0128
PerceptionR1Backbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0127.6
GRPOBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0127.6
OpenVLThinkerBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0127.5
PAPOBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0126.5
Look-BackBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0125.8
CPPOBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0125.3
Vision-MattersBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0125.2
GRPOBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0125.1
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B, Sampling Strategy=avg@8, Inference Temperature=12026.0124.5
PAPOBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0124.3
OpenVLThinkerBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0122.3
Visionary-R1Backbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0119.7
Qwen2.5-VL-3BBackbone=Qwen2.5-VL-3B, Sampling Strategy=avg@8, Inference Temperature=12026.0119.5