Search Relevance on Minor Language family Qwen2.5 series benchmark (test)
84.99NDCG@1
SERM
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 84.99 | 85.12 | 55.07 | |
2026.01 | 84.79 | 85.05 | 54.4 | |
2026.01 | 84.75 | 85.03 | 54.35 | |
2026.01 | 84.55 | 84.96 | 54.24 | |
2026.01 | 84.46 | 84.93 | 54.07 | |
2026.01 | 84.43 | 84.78 | 54.42 | |
2026.01 | 84.4 | 84.6 | 53.68 | |
2026.01 | 84.11 | 84.81 | 53.51 | |
2026.01 | 82.3 | 84.12 | 53.83 | |
2026.01 | 82.29 | 84.12 | 54.25 | |
2026.01 | 82.2 | 84.08 | 54.45 | |
2026.01 | 82.19 | 84.09 | 53.74 | |
2026.01 | 82.1 | 84.05 | 53.32 | |
2026.01 | 82.02 | 84.02 | 52.89 | |
2026.01 | 82 | 84.02 | 53.09 | |
2026.01 | 81.75 | 83.91 | 51.81 | |
2026.01 | 81.65 | 83.49 | 52.86 | |
2026.01 | 81.47 | 83.5 | 53.73 |