TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Natural Language Processing/Common Sense Reasoning/PARus

Common Sense Reasoning on PARus

Metric: Accuracy (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Accuracy▼Extra DataPaperDate↕Code
1Human Benchmark0.982NoRussianSuperGLUE: A Russian Language Understandi...2020-10-29Code
2Golden Transformer0.908No---
3YaLM 1.0B few-shot0.766No---
4RuGPT3XL few-shot0.676No---
5ruT5-large-finetune0.66No---
6RuGPT3Medium0.598No---
7RuGPT3Large0.584No---
8RuBERT plain0.574No---
9RuGPT3Small0.562No---
10ruT5-base-finetune0.554No---
11Multilingual Bert0.528No---
12ruRoberta-large finetune0.508No---
13RuBERT conversational0.508No---
14MT5 Large0.504NomT5: A massively multilingual pre-trained text-t...2020-10-22Code
15SBERT_Large_mt_ru_finetuning0.498No---
16SBERT_Large0.498No---
17majority_class0.498NoUnreasonable Effectiveness of Rule-Based Heurist...2021-05-03-
18ruBert-large finetune0.492No---
19Baseline TF-IDF1.10.486NoRussianSuperGLUE: A Russian Language Understandi...2020-10-29Code
20Random weighted0.48NoUnreasonable Effectiveness of Rule-Based Heurist...2021-05-03-
21heuristic majority0.478NoUnreasonable Effectiveness of Rule-Based Heurist...2021-05-03-
22ruBert-base finetune0.476No---