| Paper | Code | MCC | ModelName | ReleaseDate |
|---|---|---|---|---|
| RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark | ✓ Link | 0.626 | Human Benchmark | 2020-10-29 |
| []() | 0.339 | ruRoberta-large finetune | ||
| []() | 0.32 | ruT5-large-finetune | ||
| []() | 0.267 | ruT5-base-finetune | ||
| []() | 0.235 | ruBert-large finetune | ||
| []() | 0.231 | RuGPT3Large | ||
| []() | 0.224 | ruBert-base finetune | ||
| []() | 0.218 | SBERT_Large_mt_ru_finetuning | ||
| []() | 0.209 | SBERT_Large | ||
| []() | 0.191 | RuBERT plain | ||
| []() | 0.189 | Multilingual Bert | ||
| []() | 0.178 | RuBERT conversational | ||
| Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks | 0.147 | heuristic majority | 2021-05-03 | |
| []() | 0.124 | YaLM 1.0B few-shot | ||
| []() | 0.096 | RuGPT3XL few-shot | ||
| mT5: A massively multilingual pre-trained text-to-text transformer | ✓ Link | 0.061 | MT5 Large | 2020-10-22 |
| RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark | ✓ Link | 0.06 | Baseline TF-IDF1.1 | 2020-10-29 |
| []() | 0.01 | RuGPT3Medium | ||
| []() | 0 | Golden Transformer | ||
| Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks | 0 | Random weighted | 2021-05-03 | |
| Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks | 0 | majority_class | 2021-05-03 | |
| []() | -0.013 | RuGPT3Small |