Prompt Adherence Evaluation on DB-3DME 1.0 (test)
0.483Pearson R
ChatGPT-5-high
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 0.483 | 64.3 | 96.4 | |
2026.06 | 0.472 | 64.5 | 95.4 | |
2026.06 | 0.468 | 63.7 | 96.3 | |
2026.06 | 0.459 | 64.9 | 95.6 | |
2026.06 | 0.454 | 64.8 | 94 | |
2026.06 | 0.452 | 63.6 | 94 | |
2026.06 | 0.451 | 63.9 | 95.6 | |
2026.06 | 0.427 | 64 | 94.5 | |
2026.06 | 0.414 | 64.4 | 94 | |
2026.06 | 0.413 | 64.1 | 94.2 | |
2026.06 | 0.404 | 60.2 | 94.4 | |
2026.06 | 0.393 | 60.5 | 93.9 | |
2026.06 | 0.232 | 50 | 87.2 | |
2026.06 | 0.228 | - | - | |
2026.06 | 0.214 | 50.7 | 83.7 |