Pairwise preference ranking on Held-out
1,187ELO Score
Human Abstracts
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.10 | 1,187 | 17 | 1 | 94.4 | |
2025.10 | 1,119 | 14 | 5 | 63.6 | |
2025.10 | 939 | 5 | 8 | 25 | |
2025.10 | 927 | 5 | 12 | 25 | |
2025.10 | 828 | 1 | 16 | 5 |
Human Abstracts
| Method | Links | ||||
|---|---|---|---|---|---|
2025.10 | 1,187 | 17 | 1 | 94.4 | |
2025.10 | 1,119 | 14 | 5 | 63.6 | |
2025.10 | 939 | 5 | 8 | 25 | |
2025.10 | 927 | 5 | 12 | 25 | |
2025.10 | 828 | 1 | 16 | 5 |