List your company
ResearchFormerly WizWand

Math Reasoning on MathVista (Score)

78.8ScoreVisPlay-8B-iter3
47.39255.54663.771.854Mar 4, 2026Mar 16, 2026Mar 28, 2026Apr 9, 2026Apr 21, 2026May 3, 2026May 16, 2026
Updated 5mo ago

Evaluation results

MethodLinks
VisPlay-8B-iter3Model Category=Pseudo-label-based Self-evolution Methods, Scale=8B, Iteration=32026.0478.8
Jigsaw-R1-8BModel Category=Template-based Self-evolution Methods, Scale=8B2026.0477.9
EVE (Ours-8B-iter4)Model Category=Pseudo-label-based Self-evolution Methods, Scale=8B, Iteration=42026.0477.9
Qwen3-VL-8B-InstructModel Category=Open-Source MLLMs, Scale=8B2026.0476.9
HEEDMethod ID=C4, Distillation Strategy=HEED, Training Stage=Before SFT+DPO2026.0576.2
TeacherMethod ID=C0, Distillation Strategy=Teacher, Training Stage=Before SFT+DPO2026.0576
RSAMethod ID=C3, Distillation Strategy=RSA, Training Stage=Before SFT+DPO2026.0575.5
HSAMethod ID=C2, Distillation Strategy=HSA, Training Stage=Before SFT+DPO2026.0575.4
ThinkLite-VLModel Category=Multimodal Reasoning Models2026.0375.1
KDMethod ID=C1, Distillation Strategy=KD, Training Stage=Before SFT+DPO2026.0574.9
AVAR-ThinkerModel Category=Our model2026.0374.7
MM-Zero-8B-iter3Model Category=Pseudo-label-based Self-evolution Methods, Scale=8B, Iteration=32026.0474.7
Claude-3.7-SonnetModel Category=Closed-Source2026.0374.5
Vision-R1Model Category=Multimodal Reasoning Models, Trained on MathVision=True2026.0373.5
MM-Eureka-7BModel Category=Multimodal Reasoning Models2026.0373
OpenVLThinkerModel Category=Multimodal Reasoning Models2026.0372.3
GPT-5 nano (high)Model Category=Closed-Source MLLMs, Scale=high2026.0471.5
InternVL3-9BModel Category=Open-Source MLLMs, Scale=9B2026.0471.5
Qwen2.5-VL-7BModel Category=Open-Source General Models2026.0368.2
Vision-SR1Model Category=Multimodal Reasoning Models2026.0368.1
VLAA-Thinker-7BModel Category=Multimodal Reasoning Models2026.0368
LLaVA-OneVision-72BModel Category=Open-Source MLLMs, Scale=72B2026.0467.1
InternVL2.5-8BModel Category=Open-Source General Models2026.0364.4
R1-OneVisionModel Category=Multimodal Reasoning Models2026.0364.1
GPT-4oModel Category=Closed-Source2026.0363.8
GPT-4o-20240513Model Category=Closed-Source MLLMs2026.0463.8
Mulberry-7BModel Category=Multimodal Reasoning Models, Trained on MathVision=True2026.0363.1
GPT-5 mini (minimal)Model Category=Closed-Source MLLMs, Scale=minimal2026.0459.6
LLaVA-OneVision-7BModel Category=Open-Source General Models2026.0358.6
Llama-3.2-11B-Vision-InstructModel Category=Open-Source General Models2026.0348.6