Non-Agentic Performance Evaluation on Persuade (test)
53.2Mean ScoreGemini 2.5 Pro
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Gemini 2.5 Pro2026.03 | 53.2 | 11.1 | 40 | 70 | |
| LLama 4 Maverick2026.03 | 52.62 | 15.05 | 30 | 70.97 | |
| GPT-4o2026.03 | 48.43 | 16.61 | 30 | 77.42 | |
| Claude Sonnet 4.52026.03 | 37.26 | 17.18 | 20 | 60 |