Insight-level Evaluation on SCOpE-QA Legal NLP collection
4.27Insight ScoreINSIGHTGEN
Evaluation Results
| Method | Links | |
|---|---|---|
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 4.27 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 4.21 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 4.15 | |
| FAISSTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.83 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.75 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.64 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.61 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 3.43 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.37 | |
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 3.33 | |
| Direct GPTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.3 | |
| GPT+COTTarget Model=GPT-4o, Evaluator Model=Gemini-1.5-Flash2026.04 | 3.27 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.83 | |
| FAISSTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.73 | |
| GPT+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.7 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.67 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.43 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.4 | |
| Direct GPTTarget Model=GPT-4o, Evaluator Model=Claude-3-Sonnet2026.04 | 2.34 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator Model=Claude-3-Sonnet2026.04 | 2.32 |