List your company

Reasoning and Math on VLMEvalKit (test)

73.4MathVista AccuracyGemini2.0-Flash
60.9264.1667.470.64Sep 29, 2025

Evaluation results

MethodLinks
Gemini2.0-FlashModel Category=Proprietary Model2025.0973.441.357.154.456.243.754.4
VisionZero-Qwen-7B (Real-World)Backbone=Qwen2.5-VL-7B, Training Domain=Real-World2025.0973.128.540.152.150.822.544.5
MM-Eureka-Qwen-7BBackbone=Qwen2.5-VL-7B2025.097326.936.250.342.924.242.9
VisionZero-Qwen-7B (Chart)Backbone=Qwen2.5-VL-7B, Training Domain=Chart2025.0972.428.938.852.551.222.143.3
VisionZero-Qwen-7B (CLEVR)Backbone=Qwen2.5-VL-7B, Training Domain=CLEVR2025.0972.228.439.253.249.822.944.3
ViGaL-Snake+RotationBackbone=Qwen2.5-VL-7B2025.0971.927.536.952.446.522.943
ViGaL-RotationBackbone=Qwen2.5-VL-7B2025.0971.226.3—50.4———
ViGaL-SnakeBackbone=Qwen2.5-VL-7B2025.0970.726.5—51.1———
OpenVLThinker-7BBackbone=Qwen2.5-VL-7B2025.0970.225.336.547.944.321.240.9
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B2025.0968.225.436.14947.220.941.1
VLAA-Thinker-7BBackbone=Qwen2.5-VL-7B2025.096826.43651.747.221.941.9
R1-OneVision-7BBackbone=Qwen2.5-VL-7B2025.0964.124.135.847.144.521.439.5
GPT4oModel Category=Proprietary Model2025.0961.430.44050.245.932.343.4