Multi-turn dialogue on TopDial
7.71LLM-EVAL
Backbone
Updated 9d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.04 | 7.71 | 8.25 | 14.5 | 0.392 | 7.25 | |
2026.04 | 7.32 | 7.7 | 15 | 0.451 | 1.25 | |
2026.04 | 7.22 | 7.62 | 11.2 | 0.423 | 5.75 | |
2026.04 | 7.21 | 7.55 | 11.4 | 0.412 | 5.67 | |
2026.04 | 7.16 | 7.41 | 11.7 | 0.411 | 5.33 | |
2026.04 | 7.16 | 7.46 | 12.8 | 0.431 | 4.75 | |
2026.04 | 7.15 | 7.52 | 13.4 | 0.426 | 5.58 | |
2026.04 | 7.14 | 7.54 | 12.3 | 0.39 | 7.25 | |
2026.04 | 7.14 | 7.56 | 11.6 | 0.421 | 4.67 | |
2026.04 | 7.13 | 7.58 | 11 | 0.414 | 6.17 | |
2026.04 | 7.12 | 6.68 | 15.8 | 0.499 | 5 | |
2026.04 | 7.12 | 6.48 | 17.3 | 0.465 | 1.25 | |
2026.04 | 6.98 | 6.27 | 15.6 | 0.458 | 4.92 | |
2026.04 | 6.97 | 6.2 | 15.1 | 0.436 | 7 | |
2026.04 | 6.9 | 6.29 | 14.5 | 0.43 | 6 | |
2026.04 | 6.82 | 6.38 | 15.1 | 0.436 | 4.58 | |
2026.04 | 6.81 | 6.36 | 14.4 | 0.426 | 5.5 | |
2026.04 | 6.78 | 6.28 | 15.3 | 0.433 | 5.58 | |
2026.04 | 6.61 | 6.2 | 13.9 | 0.409 | 5.67 | |
2026.04 | 6.58 | 6.2 | 14 | 0.409 | 6.92 |