List your company
ResearchFormerly WizWand

Deliberation Summarization on DELIBERATIONBANK

0.622Overall Quality ScoreGPT-5-Mini
0.547120.566560.5860.60544Oct 2, 2025
Updated 6mo ago

Evaluation results

MethodLinks
GPT-5-Mini2025.100.622————
GPT-52025.100.617————
Claude-Sonnet-42025.100.615————
Claude-Opus-42025.100.614————
Qwen3-32B2025.100.609————
Gemini-2.5-Flash2025.100.605————
Grok-42025.100.594————
Gemini-2.5-Pro2025.100.594————
Qwen3-235B2025.100.593————
Qwen3-14B2025.100.584————
Qwen3-1.7B2025.100.583————
DeepSeek-Reasoner2025.100.58————
DeepSeek-Chat2025.100.576————
Qwen3-4B2025.100.575————
Qwen3-8B2025.100.575————
GPT-4o-Mini2025.100.571————
Qwen3-30B2025.100.571————
Qwen3-0.6B2025.100.55————
CoTModel=Llama-3.3-70B2026.04—0.5680.5240.570.561
CoTModel=GPT-4.1-mini2026.04—0.5810.5250.5680.571
CoTModel=GPT-4.12026.04—0.5820.5370.5720.577
DirectModel=Llama-3.3-70B2026.04—0.5860.5370.580.574
DirectModel=GPT-4.1-mini2026.04—0.5820.5340.5760.579
DirectModel=GPT-4.12026.04—0.5780.5310.5730.575
MADModel=Llama-3.3-70B2026.04—0.5880.5440.5720.579
MADModel=GPT-4.1-mini2026.04—0.5980.5530.5690.592
MADModel=GPT-4.12026.04—0.5990.5610.5760.594
Self-RefineModel=Llama-3.3-70B2026.04—0.5770.5360.5660.57
Self-RefineModel=GPT-4.1-mini2026.04—0.6080.5440.5710.593
Self-RefineModel=GPT-4.12026.04—0.5950.5560.5740.594
TeamFusionModel=Llama-3.3-70B2026.04—0.6080.5880.5870.602
TeamFusionModel=GPT-4.1-mini2026.04—0.6140.5940.5850.608
TeamFusionModel=GPT-4.12026.04—0.6210.6220.5820.619