Deep Research on ScholarQA CS
70.5Average ScoreGEPA custom
Evaluation Results
| Method | Links | |
|---|---|---|
| GEPA customPrompt Initialization=Minimal Prompt, Optimization Status=With Optimizer2026.04 | 70.5 | |
| GEPA customPrompt Initialization=Expert Prompt, Optimization Status=With Optimizer2026.04 | 70.1 | |
| GEPAPrompt Initialization=Minimal Prompt, Optimization Status=With Optimizer2026.04 | 68.5 | |
| TextGradPrompt Initialization=Expert Prompt, Optimization Status=With Optimizer2026.04 | 67.2 | |
| GEPAPrompt Initialization=Expert Prompt, Optimization Status=With Optimizer2026.04 | 67 | |
| Expert Prompt BaselinePrompt Initialization=Expert Prompt, Optimization Status=No Optimizer2026.04 | 66.7 | |
| OpenAIPrompt Initialization=Expert Prompt, Optimization Status=With Optimizer2026.04 | 66.7 | |
| TextGradPrompt Initialization=Minimal Prompt, Optimization Status=With Optimizer2026.04 | 65.4 | |
| OpenAIPrompt Initialization=Minimal Prompt, Optimization Status=With Optimizer2026.04 | 58.3 | |
| Minimal Prompt BaselinePrompt Initialization=Minimal Prompt, Optimization Status=No Optimizer2026.04 | 51.3 |