Pairwise Classification on 20 system prompts
97.1TF-IDF Accuracy
GPT-4.1-NANO
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 97.1 | -0.358 | -0.156 | |
2026.06 | 96.4 | -0.302 | -0.17 | |
2026.06 | 91.4 | -0.411 | -0.328 | |
2026.06 | 80.9 | -0.342 | -0.316 | |
2026.06 | 79.3 | -0.128 | -0.128 | |
2026.06 | 77.5 | -0.162 | -0.142 |