| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MLQA v1.0 (test) | INFOXLM | F1 (es)75.1 | 34 | 3mo ago | |
| MKQA Average across languages | CroSearch-R1 | fEM45.92 | 14 | 1mo ago | |
| MKQA Arabic | CroSearch-R1 | fEM24.12 | 14 | 1mo ago | |
| MKQA Thai | CroSearch-R1 | fEM27.83 | 14 | 1mo ago | |
| MKQA French | CroSearch-R1 | fEM59.67 | 14 | 1mo ago | |
| MKQA English | CroSearch-R1 | fEM72.07 | 14 | 1mo ago | |
| EXAMS TR | Score30.03 | 8 | 2mo ago | ||
| MLQA | INFOXLM | F1 (en)84.5 | 8 | 3mo ago | |
| Open-Ended CLQA | Llama_CL | Rank 1 Count325 | 4 | 1mo ago | |
| LEGALBENCH RuleQA English (test) | JurisMA | ROUGE-120.25 | 3 | 1mo ago |