| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| []() | 0.917 | Golden Transformer | ||
| RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark | ✓ Link | 0.915 | Human Benchmark | 2020-10-29 |
| []() | 0.82 | ruRoberta-large finetune | ||
| []() | 0.773 | ruBert-large finetune | ||
| []() | 0.732 | ruT5-base-finetune | ||
| []() | 0.712 | ruBert-base finetune | ||
| []() | 0.711 | ruT5-large-finetune | ||
| []() | 0.697 | SBERT_Large_mt_ru_finetuning | ||
| []() | 0.675 | SBERT_Large | ||
| mT5: A massively multilingual pre-trained text-to-text transformer | ✓ Link | 0.657 | MT5 Large | 2020-10-22 |
| Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks | 0.642 | heuristic majority | 2021-05-03 | |
| []() | 0.639 | RuBERT plain | ||
| []() | 0.637 | YaLM 1.0B few-shot | ||
| []() | 0.634 | RuGPT3Medium | ||
| []() | 0.624 | Multilingual Bert | ||
| RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark | ✓ Link | 0.621 | Baseline TF-IDF1.1 | 2020-10-29 |
| []() | 0.61 | RuGPT3Small | ||
| []() | 0.606 | RuBERT conversational | ||
| []() | 0.604 | RuGPT3Large | ||
| []() | 0.59 | RuGPT3XL few-shot | ||
| Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks | 0.52 | Random weighted | 2021-05-03 | |
| Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks | 0.503 | majority_class | 2021-05-03 |