List your company
ResearchFormerly WizWand

Domain Reasoning on LB

60AccuracyRM-Regen
20.594430.824741.05551.2853Mar 20, 2026
Updated 7mo ago

Evaluation results

MethodLinks
RM-RegenBase Model=GPT-3.52026.0360
RM-RegenBase Model=Llama 3.1-8B2026.0356.84
ST CoTBase Model=Llama 3.1-8B, Iterations=32026.0355.79
ST CoTBase Model=Llama 3.1-8B, Iterations=22026.0354.74
Self-RefineBase Model=GPT-3.5, Iterations=22026.0353.68
ST CoTBase Model=Llama 3.1-8B, Iterations=42026.0350.53
ProCoBase Model=GPT-3.5, Iterations=22026.0348.42
ST CoTBase Model=Llama 3.1-8B, Iterations=52026.0348.42
Self-RefineBase Model=Llama 3.1-8B, Iterations=22026.0346.32
Self-RefineBase Model=Llama 3.1-8B, Iterations=32026.0346.32
Self-RefineBase Model=Llama 3.1-8B, Iterations=52026.0344.21
ProCoBase Model=Llama 3.1-8B, Iterations=42026.0344.21
ProCoBase Model=GPT-3.5, Iterations=42026.0342.11
ProCoBase Model=GPT-3.5, Iterations=32026.0341.05
ProCoBase Model=Llama 3.1-8B, Iterations=22026.0340
Self-RefineBase Model=Llama 3.1-8B, Iterations=42026.0338.95
ProCoBase Model=Llama 3.1-8B, Iterations=32026.0338.95
ProCoBase Model=Llama 3.1-8B, Iterations=52026.0338.95
Self-RefineBase Model=GPT-3.5, Iterations=32026.0328.42
ST CoTBase Model=GPT-3.5, Iterations=22026.0325.26
ST CoTBase Model=GPT-3.5, Iterations=42026.0325.26
ST CoTBase Model=GPT-3.5, Iterations=32026.0323.16
Self-RefineBase Model=GPT-3.5, Iterations=42026.0322.11