Insight Generation on Internal Document Collections Climate Change Policy
4.34Insight-level ScoreINSIGHTGEN
Evaluation Results
| Method | Links | |
|---|---|---|
| INSIGHTGENTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 4.34 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 4.28 | |
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 4.19 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 4.15 | |
| Direct GPTTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.82 | |
| GPT+COTTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.75 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.66 | |
| FAISSTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.35 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 3.35 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 3.18 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 3.07 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.97 | |
| Direct GPTTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.66 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 2.63 | |
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.6 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.59 | |
| GPT+COTTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.58 | |
| FAISSTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.38 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.11 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 1.92 |