| visual-question-answering-on-v-bench | Penguin-VL 8B | #3 | Accuracy: 90.1 |
| visual-question-answering-on-v-bench | Penguin-VL 2B | #17 | Accuracy: 74.9 |
| visual-question-answering-on-docvqa-test | Penguin-VL 8B | #6 | ANLS: 0.961 |
| visual-question-answering-on-docvqa-test | Penguin-VL 2B | #20 | ANLS: 0.933 |
| zero-shot-video-question-answer-on-egoschema-fullset | Penguin-VL 8B | #7 | Accuracy: 70.2 |
| zero-shot-video-question-answer-on-egoschema-fullset | Penguin-VL 2B | #35 | Accuracy: 55.7 |
| optical-character-recognition-ocr-on-ocrbench | Penguin-VL 8B | #8 | Score: 896 |
| visual-question-answering-vqa-on-blink | Penguin-VL 8B | #8 | Accuracy: 69.1 |
| visual-question-answering-vqa-on-blink | Penguin-VL 2B | #40 | Accuracy: 53.8 |
| chart-question-answering-on-charxiv-dq | Penguin-VL 8B | #11 | Accuracy: 83.0 |
| chart-question-answering-on-charxiv-dq | Penguin-VL 2B | #16 | Accuracy: 62.3 |
| mathematical-reasoning-on-mathverse | Penguin-VL 8B | #11 | Accuracy: 62.1 |
| mathematical-reasoning-on-mathverse | Penguin-VL 2B | #17 | Accuracy: 52.1 |
| chart-question-answering-on-chartqa | Penguin-VL 8B | #12 | 1:1 Accuracy: 89.6 |
| chart-question-answering-on-chartqa | Penguin-VL 2B | #74 | 1:1 Accuracy: 76.9 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | Penguin-VL (8B) | #23 | Accuracy (%): 71.4 |
| chart-question-answering-on-charxiv-rq | Penguin-VL 8B | #24 | Accuracy: 46.4 |
| chart-question-answering-on-charxiv-rq | Penguin-VL 2B | #29 | Accuracy: 26.8 |
| video-question-answering-on-mmvu | Penguin-VL 8B | #25 | Accuracy: 58.7 |
| video-question-answering-on-mmvu | Penguin-VL 2B | #32 | Accuracy: 41.7 |
| multimodal-reasoning-on-mmmu-pro | Penguin-VL 8B | #35 | Accuracy: 55.9 |
| multimodal-reasoning-on-mmmu-pro | Penguin-VL 2B | #56 | Accuracy: 36.5 |
| multimodal-reasoning-on-mathvista | Penguin-VL 8B | #38 | Accuracy: 77.2 |
| multimodal-reasoning-on-mathvista | Penguin-VL 2B | #92 | Accuracy: 61.3 |
| video-question-answering-on-mvbench | Penguin-VL 8B | #39 | Avg.: 68.7 |
| video-question-answering-on-mvbench | Penguin-VL 2B | #63 | Avg.: 61.7 |
| visual-question-answering-vqa-on-realworldqa | Penguin-VL 8B | #43 | Accuracy: 71.5 |
| visual-question-answering-vqa-on-realworldqa | Penguin-VL 2B | #73 | Accuracy: 63.9 |
| moment-retrieval-on-charades-sta | Penguin-VL 8B | #49 | R@1 IoU=0.5: 56.0 |
| moment-retrieval-on-charades-sta | Penguin-VL 2B | #53 | R@1 IoU=0.5: 54.5 |