Metric: Average F1 (higher is better)
| # | Model↕ | Average F1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Golden Transformer | 0.941 | No | - | - | - |
| 2 | MT5 Large | 0.844 | No | mT5: A massively multilingual pre-trained text-t... | 2020-10-22 | Code |
| 3 | ruRoberta-large finetune | 0.83 | No | - | - | - |
| 4 | ruT5-large-finetune | 0.815 | No | - | - | - |
| 5 | Human Benchmark | 0.806 | No | RussianSuperGLUE: A Russian Language Understandi... | 2020-10-29 | Code |
| 6 | ruT5-base-finetune | 0.769 | No | - | - | - |
| 7 | ruBert-large finetune | 0.76 | No | - | - | - |
| 8 | ruBert-base finetune | 0.742 | No | - | - | - |
| 9 | RuGPT3XL few-shot | 0.74 | No | - | - | - |
| 10 | RuGPT3Large | 0.729 | No | - | - | - |
| 11 | RuBERT plain | 0.711 | No | - | - | - |
| 12 | RuGPT3Medium | 0.706 | No | - | - | - |
| 13 | RuBERT conversational | 0.687 | No | - | - | - |
| 14 | YaLM 1.0B few-shot | 0.673 | No | - | - | - |
| 15 | heuristic majority | 0.671 | No | Unreasonable Effectiveness of Rule-Based Heurist... | 2021-05-03 | - |
| 16 | RuGPT3Small | 0.653 | No | - | - | - |
| 17 | SBERT_Large | 0.646 | No | - | - | - |
| 18 | SBERT_Large_mt_ru_finetuning | 0.642 | No | - | - | - |
| 19 | Multilingual Bert | 0.639 | No | - | - | - |
| 20 | Baseline TF-IDF1.1 | 0.587 | No | RussianSuperGLUE: A Russian Language Understandi... | 2020-10-29 | Code |
| 21 | Random weighted | 0.45 | No | Unreasonable Effectiveness of Rule-Based Heurist... | 2021-05-03 | - |
| 22 | majority_class | 0 | No | - | - | - |