Search Relevance on Romance language family Qwen2.5 series benchmark (test)
88.14NDCG@1
SERM
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 88.14 | 88.27 | 53.51 | |
2026.01 | 88.01 | 88.22 | 53.25 | |
2026.01 | 87.83 | 88.16 | 53.25 | |
2026.01 | 87.72 | 88.12 | 52.74 | |
2026.01 | 87.68 | 87.84 | 52.74 | |
2026.01 | 87.68 | 88.09 | 52.55 | |
2026.01 | 87.46 | 88.02 | 51.98 | |
2026.01 | 86.96 | 87.33 | 52.7 | |
2026.01 | 86.07 | 87.51 | 51.08 | |
2026.01 | 85.99 | 87.44 | 50.24 | |
2026.01 | 85.98 | 87.47 | 51.22 | |
2026.01 | 85.86 | 87.43 | 51.6 | |
2026.01 | 85.82 | 87.43 | 51.4 | |
2026.01 | 85.72 | 87.35 | 51.85 | |
2026.01 | 85.61 | 87.33 | 50.74 | |
2026.01 | 85.58 | 87.33 | 51.85 | |
2026.01 | 84.88 | 86.79 | 50.83 | |
2026.01 | 84.75 | 86.68 | 50.98 |