| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-task Language Evaluation | FineTasks average across languages | Average Rank4.35 | 7 | |
| Aggregate Benchmark Evaluation | FineTasks Turkish (test) | Score0.204 | 5 | |
| Aggregate Benchmark Evaluation | FineTasks Arabic (test) | Score0.161 | 5 | |
| Multilingual Language Model Evaluation | FineTasks French (test) | Average Rank1.8333 | 4 | |
| Aggregate Benchmark Evaluation | FineTasks Hindi (test) | Score8.9 | 4 |