List your company
ResearchFormerly WizWand

Insight-level Evaluation on SCOpE-QA Inference Optimization collection

4.49Insight-level ScoreINSIGHTGEN
2.03562.67283.313.9472Apr 21, 2026
Updated 6mo ago

Evaluation results

MethodLinks
INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.044.49
FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.044.09
Direct GPTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.044.02
GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.044
FAISSTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.98
INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.98
Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.043.7
FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.043.67
GPT+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.48
FAISS+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.42
INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.043.13
INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.043.03
FAISSTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.89
Direct GPTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.78
FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.67
FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.64
Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.57
GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.51
FAISS+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.3
GPT+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.13