| video-question-answering-on-tempcompass-overall | SmolVLM 2.2B | #16 | Accuracy: 53.7 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | SmolVLM 2.2B | #52 | Accuracy (%): 52.1 |
| video-question-answering-on-mlvu | SmolVLM 2.2B | #54 | Accuracy: 55.2 |
| optical-character-recognition-ocr-on-ocrbench | SmolVLM 2.2B | #60 | Score: 729 |
| visual-question-answering-on-docvqa-test | SmolVLM 2.2B | #72 | ANLS: 0.800 |
| video-question-answering-on-mvbench | SmolVLM 2.2B | #80 | Avg.: 46.3 |
| vision-language-understanding-on-mmstar | SmolVLM 2.2B | #95 | Accuracy: 46.0 |
| chart-question-answering-on-chartqa | SmolVLM 2.2B | #96 | 1:1 Accuracy: 68.7 |
| multimodal-reasoning-on-mathvista | SmolVLM 2.2B | #105 | Accuracy: 51.5 |
| multimodal-reasoning-on-mmmu | SmolVLM 2.2B | #120 | Accuracy: 42.0 |