Leaderboard

Rank Name Team Info Score Diagnostic RCB PARus MuSeRC TERRa RUSSE RWSD DaNetQA RuCoS
1 HUMAN BENCHMARK AGI NLP 0.802 0.626 0.68/0.702 0.982 0.806/0.42 0.92 0.747 0.84 0.879 0.93/0.924
2 RuBERT conversational AGI NLP 0.546 0.186 0.432/0.468 0.61 0.656/0.256 0.639 0.894 0.675 0.749 0.255/0.251
3 Multilingual BERT AGI NLP 0.542 0.157 0.365/0.425 0.588 0.626/0.253 0.62 0.84 0.675 0.79 0.371/0.367
4 GPT2-large_bbpe_v50 AGI NLP 0.539 0.099 0.406/0.447 0.58 0.699/0.327 0.699 0.835 0.688 0.756 0.25/0.248
5 mBART - 0.536 -0.003 0.288/0.395 0.528 0.477/0.03 0.508 0.99 0.649 0.742 0.82/0.816
6 Plain RuBERT DeepPavlov 0.524 -0.026 0.338/0.393 0.532 0.712/0.309 0.636 0.877 0.662 0.78 0.38/0.379
7 GPT2-medium_bbpe_v50 AGI NLP 0.492 -0.047 0.368/0.438 0.584 0.692/0.278 0.605 0.804 0.597 0.756 0.24/0.241
8 GPT2-small_bbpe_v50 AGI NLP 0.491 0.054 0.421/0.445 0.544 0.693/0.256 0.514 0.743 0.675 0.766 0.22/0.217
9 Slavic BERT DeepPavlov 0.483 -0.01 0.34/0.418 0.526 0.677/0.27 0.566 0.829 0.578 0.759 0.24/0.242
10 Baseline TF-IDF AGI NLP 0.372 -0.004 0.288/0.395 0.522 0.477/0.03 0.496 0.632 0.338 0.763 0.0/0.002