Insight Generation on Internal document collections Instagram Marketing
4.76Insight Level ScoreINSIGHTGEN
Evaluation Results
| Method | Links | |
|---|---|---|
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 4.76 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 4.59 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 4.4 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 4.06 | |
| Direct GPTTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.9 | |
| GPT+COTTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.75 | |
| FAISSTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.67 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator=Gemini-2.5-Flash2026.04 | 3.54 | |
| INSIGHTGENTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 3.48 | |
| INSIGHTGENTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 3.37 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 3.19 | |
| FAISS+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.95 | |
| GPT+COTTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.68 | |
| Direct GPTTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.49 | |
| GPT+COTTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.49 | |
| FAISSTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.4 | |
| FAISS+COTTarget Model=GPT-4o, Evaluator=Claude-4-Sonnet2026.04 | 2.39 | |
| Direct GPTTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 2.25 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator=Gemini-2.5-Flash2026.04 | 2.02 | |
| FAISSTarget Model=Claude-3.5-Sonnet, Evaluator=Claude-4-Sonnet2026.04 | 1.5 |