Text-Based Optimization on Code Domain (test)
89.89AccuracyCRITIQ Scorer
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CRITIQ Scorer2025.02 | 89.89 | 7.87 | |
| CRITIQ Flow2025.02 | 89.33 | 7.31 | |
| Vanilla2025.02 | 82.02 | — | |
| TextGrad2025.02 | 72.7 | -9.32 | |
| DRPO2025.02 | 68.99 | -13.03 |
| Method | Links | ||
|---|---|---|---|
| CRITIQ Scorer2025.02 | 89.89 | 7.87 | |
| CRITIQ Flow2025.02 | 89.33 | 7.31 | |
| Vanilla2025.02 | 82.02 | — | |
| TextGrad2025.02 | 72.7 | -9.32 | |
| DRPO2025.02 | 68.99 | -13.03 |