Таблица скроллится влево
| Борд | Результат | Attempted Score | Coverage | Место в рейтинге |
|---|---|---|---|---|
| Мульти | 0.116 | 0.174 | 0.667 | 28 |
| Изображения | 0.165 | 0.165 | 1 | 33 |
| Видео | 0.205 | 0.205 | 1 | 31 |
Таблица скроллится влево
| Задача | Модальность | Результат | Метрика |
|---|---|---|---|
| WEIRD | 0.2 |
EM
JudgeScore
|
|
| RealVQA | 0.168 |
EM
JudgeScore
|
|
| ruCLEVR | 0.22 |
EM
JudgeScore
|
|
| LabTabVQA | 0.047 |
EM
JudgeScore
|
|
| ruMathVQA | 0.045 |
EM
JudgeScore
|
|
| RealVideoQA | 0.271 |
EM
JudgeScore
|
|
| ruCommonVQA | 0.278 |
EM
JudgeScore
|
|
| ruHHH-Image | 0.058 |
EM
JudgeScore
|
|
| ruHHH-Video | 0.125 |
EM
JudgeScore
|
|
| ruTiE-Image | 0.298 |
EM
JudgeScore
|
|
| CommonVideoQA | 0.219 |
EM
JudgeScore
|
|
| UniScienceVQA | 0.112 |
EM
JudgeScore
|
|
| culture | 0.081 / 0.13 | ||
| business | 0.101 / 0.17 | ||
| medicine | 0.063 / 0.131 | ||
| social_sciences | 0.136 / 0.217 | ||
| fundamental_sciences | 0.061 / 0.12 | ||
| applied_sciences | 0.107 / 0.177 | ||
| SchoolScienceVQA | 0.207 |
EM
JudgeScore
|
|
| biology | 0.043 / 0.425 | ||
| chemistry | 0.03 / 0.335 | ||
| physics | 0.029 / 0.414 | ||
| economics | 0.038 / 0.321 | ||
| ru | 0.039 / 0.323 | ||
| all | 0.02 / 0.428 | ||
| ruNaturalScienceVQA | 0.183 |
EM
JudgeScore
|
|
| biology | 0 / 0.158 | ||
| chemistry | 0.075 / 0.209 | ||
| physics | 0.045 / 0.389 | ||
| science | 0.049 / 0.415 | ||