Insight-level Evaluation on SCOpE-QA Dialogue Systems collection
4.43Insight ScoreINSIGHTGEN
Evaluation Results
| Method | Links | |
|---|---|---|
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 4.43 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 4.09 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.8 | |
| FAISSTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.7 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.63 | |
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 3.34 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.27 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 3.25 | |
| Direct GPTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.23 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 2.71 | |
| GPT+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 2.66 | |
| FAISSTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.63 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 2.63 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.6 | |
| GPT+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.41 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.36 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.3 | |
| Direct GPTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.28 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.14 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 1.86 |