List your company

Visual Mathematical Reasoning on MathVista (BoN@8)

83.5BoN@8 AccuracyInternVL2.5-38B + EVPV-PRM
58.373664.896871.4277.9432Mar 17, 2026Mar 18, 2026Mar 19, 2026Mar 20, 2026Mar 21, 2026Mar 22, 2026Mar 24, 2026

Evaluation results

MethodLinks
InternVL2.5-38B + EVPV-PRMPolicy Model=InternVL2.5-38B, Process Reward Model (PRM)=EVPV-PRM, Reranking Strategy=Best-of-82026.0383.511.6
InternVL2.5-26B + EVPV-PRMPolicy Model=InternVL2.5-26B, Process Reward Model (PRM)=EVPV-PRM, Reranking Strategy=Best-of-82026.0379.611.4
InternVL2.5-8B + EVPV-PRMPolicy Model=InternVL2.5-8B, Process Reward Model (PRM)=EVPV-PRM, Reranking Strategy=Best-of-82026.0376.311.8
InternVL2.5-38B + VisualPRMPolicy Model=InternVL2.5-38B, Process Reward Model (PRM)=VisualPRM, Reranking Strategy=Best-of-82026.0373.92
InternVL2.5-26B + VisualPRMPolicy Model=InternVL2.5-26B, Process Reward Model (PRM)=VisualPRM, Reranking Strategy=Best-of-82026.0373.14.9
InternVL2.5-38BPolicy Model=InternVL2.5-38B, Process Reward Model (PRM)=None, Reranking Strategy=Best-of-82026.0371.9—
Gemini-2.0-FlashReranking Strategy=Best-of-82026.0370.4—
InternVL2.5-8B + VisualPRMPolicy Model=InternVL2.5-8B, Process Reward Model (PRM)=VisualPRM, Reranking Strategy=Best-of-82026.0368.54
InternVL2.5-26BPolicy Model=InternVL2.5-26B, Process Reward Model (PRM)=None, Reranking Strategy=Best-of-82026.0368.2—
Claude-3.5-SonnetReranking Strategy=Best-of-82026.0365.3—
InternVL2.5-8BPolicy Model=InternVL2.5-8B, Process Reward Model (PRM)=None, Reranking Strategy=Best-of-82026.0364.5—
PEPO_GBackbone=Qwen2.5-VL-3B-Instruct, Training Data=ViRL39K2026.0363.48—
PAPO_GBackbone=Qwen2.5-VL-3B-Instruct, Training Data=ViRL39K2026.0361.38—
GPT-4oReranking Strategy=Best-of-82026.0360—
GRPOBackbone=Qwen2.5-VL-3B-Instruct, Training Data=ViRL39K2026.0359.34—