List your company

Mathematical Reasoning on Math Math500 Minerva

80.9Math500 ScoreUR2 (GPT Summary)
43.56453.25762.9572.643Aug 8, 2025Sep 25, 2025Nov 13, 2025Jan 1, 2026Feb 19, 2026Apr 9, 2026May 28, 2026

Evaluation results

MethodLinks
UR2 (GPT Summary)Backbone=Qwen-2.5-7B2025.0880.96171
Open-Reasoner-ZeroBackbone=Qwen-2.5-7B, Category=CoT-RL Methods2025.0880.758.869.8
UR2 (qw Summary)Backbone=Qwen-2.5-7B2025.0880.259.469.8
Search-o1Backbone=GPT-4o-mini, Category=Advanced RAG Methods2025.0878.668.373.5
Vanilla RLBackbone=Qwen-2.5-7B2025.0878.259.468.8
CoTBackbone=GPT-4o-mini2025.087865.671.8
RATBackbone=GPT-4o-mini, Category=Advanced RAG Methods2025.0877.564.270.9
Standard RAGBackbone=GPT-4o-mini2025.0877.168.472.8
SimpleRL-ZooBackbone=Qwen-2.5-7B, Category=CoT-RL Methods2025.0877.150.763.9
CoTBackbone=Qwen-2.5-7B2025.0876.659.468
General ReasonerBackbone=Qwen-2.5-7B, Category=CoT-RL Methods2025.0876.662.168.8
Standard RAGBackbone=Qwen-2.5-7B2025.0873.854.664.2
UR2 (qw summary)Backbone=Qwen-2.5-3B2025.0868.447.457.9
Vanilla RLBackbone=Qwen-2.5-3B2025.086843.956
UR2 (GPT summary)Backbone=Qwen-2.5-3B2025.0867.84557.2
Standard RAGBackbone=Qwen-2.5-3B2025.0865.340.853.1
CoTBackbone=Qwen-2.5-3B2025.0863.639.951.8
Self-AskBackbone=GPT-4o-mini, Category=Advanced RAG Methods2025.0862.945.254.1
SAWG1=true, G2=true, G3=true, G4=true2026.0555.113.4234.26
STRG1=true, G2=true, G3=false, G4=true2026.0554.911.3133.11
UR2 (GPT summary)Backbone=LLaMA-3.1-8B2025.0854.53946.8
DELTG1=true, G2=true, G3=false, G4=false2026.0549.212.0430.62
UR2 (qw summary)Backbone=LLaMA-3.1-8B2025.0848.638.443.5
CoTBackbone=LLaMA-3.1-8B2025.0848.434.441.4
CLG1=true, G2=false, G3=true, G4=false2026.0545.710.4828.09
RandomG1=false, G2=true, G3=false, G4=true2026.0545.659.2827.47
Vanilla RLBackbone=LLaMA-3.1-8B2025.0845.543.444.4
Standard RAGBackbone=LLaMA-3.1-8B2025.084531.438.2