List your company
ResearchFormerly WizWand

Multimodal Reasoning on MathVerse VO

48.71FEI ScoreMiMo-VL-7B
23.59430.114536.63543.1555Aug 5, 2025
Updated 5mo ago

Evaluation results

MethodLinks
MiMo-VL-7B# Samples=unk2025.0848.7166.15
VRPRM-MiMo w/o RL# Samples=3.6K, Explicit Reasoning (CoT)=true, RL Training=false2025.0848.4661.87
VRPRM-MiMo# Samples=53.6K, Explicit Reasoning (CoT)=true, RL Training=true2025.0847.9571.93
Qwen2.5-VL-7B# Samples=unk2025.0846.6942.75
VRPRM-MiMo w/o RL & w/o CoT# Samples=3.6K, Explicit Reasoning (CoT)=false, RL Training=false2025.0846.6946.55
VRPRM-Qwen3 w/o RL# Samples=3.6K, Explicit Reasoning (CoT)=true, RL Training=false2025.0846.4957.46
VRPRM-Qwen3 w/o RL & w/o CoT# Samples=3.6K, Explicit Reasoning (CoT)=false, RL Training=false2025.0846.3953.72
Qwen3-VL-4B-Thinking# Samples=unk2025.0846.263.86
VRPRM-MiMo w/o CoT# Samples=53.6K, Explicit Reasoning (CoT)=false, RL Training=true2025.0845.4271.05
VRPRM-Qwen3# Samples=53.6K, Explicit Reasoning (CoT)=true, RL Training=true2025.0844.9370.19
VRPRM w/o RL# Samples=3.6K, Explicit Reasoning (CoT)=true, RL Training=false2025.0843.9662.43
InternVL2.5-8B# Samples=unk2025.0842.9643.62
Qwen2.5-VL-72B# Samples=unk2025.0842.545.92
VRPRM w/o RL & w/o CoT# Samples=3.6K, Explicit Reasoning (CoT)=false, RL Training=false2025.0841.7251.7
VRPRM# Samples=53.6K, Explicit Reasoning (CoT)=true, RL Training=true2025.0840.9463.8
VRPRM-Qwen3 w/o CoT# Samples=53.6K, Explicit Reasoning (CoT)=false, RL Training=true2025.0838.9967.23
Gemini-2.0-Flash# Samples=unk2025.0836.1640.89
VRPRM w/o CoT# Samples=53.6K, Explicit Reasoning (CoT)=false, RL Training=true2025.0834.854.72
GPT-4o-mini# Samples=unk2025.0828.3634.44
VisualPRM-8B# Samples=400K2025.0824.5660.93