Common Sense Reasoning On Rwsd
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||
|---|---|---|---|
| Human Benchmark | 0.84 | RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark | |
| SBERT_Large_mt_ru_finetuning | 0.675 | - | - |
| RuBERT conversational | 0.669 | - | - |
| ruT5-large-finetune | 0.669 | - | - |
| Multilingual Bert | 0.669 | - | - |
| MT5 Large | 0.669 | mT5: A massively multilingual pre-trained text-to-text transformer | |
| RuGPT3Medium | 0.669 | - | - |
| heuristic majority | 0.669 | Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks | - |
| YaLM 1.0B few-shot | 0.669 | - | - |
| RuGPT3Small | 0.669 | - | - |
| ruBert-large finetune | 0.669 | - | - |
| ruBert-base finetune | 0.669 | - | - |
| majority_class | 0.669 | Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks | - |
| RuBERT plain | 0.669 | - | - |
| ruT5-base-finetune | 0.669 | - | - |
| Baseline TF-IDF1.1 | 0.662 | RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark | |
| SBERT_Large | 0.662 | - | - |
| RuGPT3XL few-shot | 0.649 | - | - |
| RuGPT3Large | 0.636 | - | - |
| Random weighted | 0.597 | Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks | - |
0 of 22 row(s) selected.