List your company
ResearchFormerly WizWand

Insight-level Evaluation on SCOpE-QA Reinforcement Learning collection

4.52Insight-level ScoreINSIGHTGEN
1.1922.0562.923.784Apr 21, 2026
Updated 6mo ago

Evaluation results

MethodLinks
INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.044.52
INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.044.18
FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.043.82
FAISSTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.72
FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.043.41
GPT+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.35
FAISS+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.34
Direct GPTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.31
INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.043.2
INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.043.2
Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.042.92
GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.042.85
FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.54
FAISSTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.51
FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.49
FAISS+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.27
Direct GPTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.11
GPT+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.041.7
Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.041.32
GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.041.32