| ,model,NUM_Q_multich_EM,NUM_Q_multich_CC,NUM_Q_multich_PM,NUM_Q_onech_EM,NUM_Q_seq_EM,NUM_Q_seq_CC,NUM_Q_seq_PM,NUM_Q_map_EM,NUM_Q_map_CC,NUM_Q_map_PM,OPEN_Q_EM,OPEN_Q_F1,OPEN_Q_LR,LEADERBOARD,Доступ,Команда/страна | |
| 0,GigaChat-2-Max,81.0,84.0,88.0,91.0,75.0,75.0,75.0,66.0,66.0,72.0,52.0,60.0,73.0,73.6923076923077,API,"СБЕР, Россия" | |
| 1,claude-3-5-sonnet,84.0,85.0,90.0,94.0,73.0,73.0,73.0,43.0,44.0,46.0,63.0,69.0,78.0,70.38461538461539,API,"Anthropic, США " | |
| 2,gemini-pro-1.5,73.0,78.0,84.0,91.0,66.0,66.0,66.0,59.0,60.0,66.0,55.00000000000001,67.0,77.0,69.84615384615384,API,"Google DeepMind, США " | |
| 3,deepseek-r1,79.0,82.0,86.0,67.0,82.0,82.0,82.0,57.99999999999999,61.0,59.0,22.0,61.0,69.0,68.46153846153847,API,"DeepSeek, Китай " | |
| 7,gpt-4o,77.0,81.0,86.0,94.0,64.0,64.0,66.0,22.0,22.0,29.0,11.0,64.0,72.0,57.84615384615385,API,"OpenAI, США " | |
| 11,GigaChat-Pro,61.0,64.0,76.0,79.0,45.0,45.0,45.0,25.0,25.0,30.0,48.0,55.00000000000001,68.0,51.23076923076923,API,"СБЕР, Россия" | |
| 12,GigaChat-Max,73.0,76.0,83.0,85.0,38.0,38.0,38.0,16.0,16.0,23.0,48.0,55.00000000000001,69.0,50.61538461538461,API,"СБЕР, Россия" | |
| 13,YandexGPT4-Pro,31.0,35.0,77.0,85.0,35.0,35.0,54.0,21.0,21.0,47.0,45.0,56.00000000000001,69.0,47.0,API,"Яндекс, Россия " | |
| 14,YandexGPT4-Pro-32k,31.0,34.0,77.0,85.0,34.0,34.0,55.00000000000001,21.0,21.0,47.0,45.0,56.99999999999999,69.0,46.92307692307692,API,"Яндекс, Россия " | |
| 16,GigaChat-Lite,56.99999999999999,61.0,72.0,75.0,38.0,38.0,38.0,13.0,13.0,17.0,35.0,42.0,56.99999999999999,42.76923076923077,API,"СБЕР, Россия" | |
| 22,YandexGPT4-Lite,33.0,38.0,57.99999999999999,74.0,6.0,6.0,7.000000000000001,2.0,2.0,5.0,35.0,52.0,66.0,29.53846153846154,API,"Яндекс, Россия " | |