List your company
ResearchFormerly WizWand

Insight-level Evaluation on SCOpE-QA Quantization collection

4.42Insight ScoreINSIGHTGEN
1.79922.47963.163.8404Apr 21, 2026
Updated 6mo ago

Evaluation results

MethodLinks
INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.044.42
FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.044.01
INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.89
FAISSTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.86
Direct GPTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.8
FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.043.72
FAISS+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.39
GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.043.33
INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.043.18
Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.043.08
GPT+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.042.99
INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.99
Direct GPTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.83
FAISSTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.78
FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.66
FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.56
Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.48
GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.3
FAISS+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.26
GPT+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.041.9