List your company
ResearchFormerly WizWand

Domain Reasoning on Headline

73AccuracyRM-Regen
4753.7560.567.25Mar 20, 2026
Updated 7mo ago

Evaluation results

MethodLinks
RM-RegenBase Model=Llama 3.1-8B2026.0373
RM-RegenBase Model=GPT-3.52026.0371
ST CoTBase Model=GPT-3.5, Iterations=22026.0370
ST CoTBase Model=GPT-3.5, Iterations=42026.0370
ProCoBase Model=GPT-3.5, Iterations=42026.0369
ST CoTBase Model=GPT-3.5, Iterations=32026.0369
ST CoTBase Model=Llama 3.1-8B, Iterations=32026.0368
ST CoTBase Model=Llama 3.1-8B, Iterations=22026.0366
ST CoTBase Model=Llama 3.1-8B, Iterations=42026.0366
ST CoTBase Model=Llama 3.1-8B, Iterations=52026.0366
ProCoBase Model=GPT-3.5, Iterations=32026.0365
Self-RefineBase Model=Llama 3.1-8B, Iterations=32026.0365
ProCoBase Model=GPT-3.5, Iterations=22026.0364
Self-RefineBase Model=Llama 3.1-8B, Iterations=42026.0363
Self-RefineBase Model=GPT-3.5, Iterations=42026.0362
Self-RefineBase Model=Llama 3.1-8B, Iterations=52026.0362
Self-RefineBase Model=Llama 3.1-8B, Iterations=22026.0360
Self-RefineBase Model=GPT-3.5, Iterations=22026.0359
Self-RefineBase Model=GPT-3.5, Iterations=32026.0353
ProCoBase Model=Llama 3.1-8B, Iterations=22026.0348
ProCoBase Model=Llama 3.1-8B, Iterations=32026.0348
ProCoBase Model=Llama 3.1-8B, Iterations=42026.0348
ProCoBase Model=Llama 3.1-8B, Iterations=52026.0348