Metric: Accuracy (higher is better)
| # | Model↕ | Accuracy▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | PaLM 2 (few-shot) | 94.4 | No | PaLM 2 Technical Report | 2023-05-17 | Code |
| 2 | mT0-13B | 84.45 | No | Crosslingual Generalization through Multitask Fi... | 2022-11-03 | Code |
| 3 | RoBERTa Large (translate test) | 76.05 | Yes | XCOPA: A Multilingual Dataset for Causal Commons... | 2020-05-01 | Code |
| 4 | BLOOMZ | 75.5 | No | Crosslingual Generalization through Multitask Fi... | 2022-11-03 | Code |
| 5 | MAD-X Base | 60.94 | Yes | MAD-X: An Adapter-Based Framework for Multi-Task... | 2020-04-30 | Code |
| 6 | mGPT | 55.5 | No | mGPT: Few-Shot Learners Go Multilingual | 2022-04-15 | Code |