Таблица скроллится влево
| Борд | Результат | Attempted Score | Coverage | Место в рейтинге |
|---|---|---|---|---|
| Мульти | 0.045 | 0.067 | 0.667 | 50 |
| Изображения | 0.011 | 0.011 | 1 | 49 |
| Видео | 0.274 | 0.274 | 1 | 24 |
Таблица скроллится влево
| Задача | Модальность | Результат | Метрика |
|---|---|---|---|
| WEIRD | 0.006 |
EM
JudgeScore
|
|
| RealVQA | 0.019 |
EM
JudgeScore
|
|
| ruCLEVR | 0.019 |
EM
JudgeScore
|
|
| LabTabVQA | 0 |
EM
JudgeScore
|
|
| ruMathVQA | 0.032 |
EM
JudgeScore
|
|
| RealVideoQA | 0.289 |
EM
JudgeScore
|
|
| ruCommonVQA | 0.023 |
EM
JudgeScore
|
|
| ruHHH-Image | 0 |
EM
JudgeScore
|
|
| ruHHH-Video | 0.243 |
EM
JudgeScore
|
|
| ruTiE-Image | 0.013 |
EM
JudgeScore
|
|
| CommonVideoQA | 0.291 |
EM
JudgeScore
|
|
| UniScienceVQA | 0.002 |
EM
JudgeScore
|
|
| culture | 0 / 0.001 | ||
| business | 0 / 0.009 | ||
| medicine | 0 / 0.003 | ||
| social_sciences | 0 / 0.007 | ||
| fundamental_sciences | 0 / 0.005 | ||
| applied_sciences | 0 / 0.01 | ||
| SchoolScienceVQA | 0.001 |
EM
JudgeScore
|
|
| biology | 0 / 0 | ||
| chemistry | 0 / 0 | ||
| physics | 0 / 0.003 | ||
| economics | 0 / 0 | ||
| ru | 0 / 0.001 | ||
| all | 0 / 0 | ||
| ruNaturalScienceVQA | 0.003 |
EM
JudgeScore
|
|
| biology | 0 / 0.018 | ||
| chemistry | 0 / 0 | ||
| physics | 0 / 0.005 | ||
| science | 0 / 0 | ||