Insight Generation on Internal document collections non-scientific domain Twitter & Mental Health
4.57Insight ScoreINSIGHTGEN
Evaluation Results
| Method | Links | |
|---|---|---|
| INSIGHTGENTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 4.57 | |
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 4.46 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 3.98 | |
| FAISSTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.63 | |
| GPT+COTTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.57 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 3.49 | |
| Direct GPTTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.44 | |
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 3.36 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 3.34 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.28 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 3.16 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 2.99 | |
| FAISSTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.69 | |
| Direct GPTTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.58 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.56 | |
| GPT+COTTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.52 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.46 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.24 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.23 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.18 |