Insight-level Evaluation on SCOpE-QA Social Computing collection
4.52Insight-level ScoreINSIGHTGEN
Evaluation Results
| Method | Links | |
|---|---|---|
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 4.52 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 4.24 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.85 | |
| FAISSTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.71 | |
| Direct GPTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.56 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.54 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 3.52 | |
| GPT+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.35 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.32 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.28 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.23 | |
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.97 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.76 | |
| FAISSTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.5 | |
| GPT+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.47 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.39 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.35 | |
| Direct GPTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.3 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.24 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.09 |