List your company
ResearchFormerly WizWand

Insight-level Evaluation on SCOpE-QA Hate Speech Detection

4.33Insight-level ScoreINSIGHTGEN
1.63642.33573.0353.7343Apr 21, 2026
Updated 6mo ago

Evaluation results

MethodLinks
INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.044.33
FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.044.29
INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.044.2
FAISSTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.83
Direct GPTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.7
FAISS+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.57
GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.043.57
FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.043.51
INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.043.39
INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.043.33
GPT+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.043.25
Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.042.94
FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.94
FAISSTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.61
FAISS+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.55
GPT+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.41
Direct GPTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.042.18
FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.042.18
GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.041.99
Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.041.74