| video-question-answering-on-mvbench | InternVL3-78B | #1 | Avg.: 78.7 |
| visual-question-answering-on-mm-vet | InternVL3-78B | #1 | GPT-4 score: 81.3 |
| visual-question-answering-vqa-on-ai2d-test-with-mask | InternVL3-78B | #1 | Accuracy: 89.7 |
| visual-question-answering-vqa-on-mme | InternVL3-78B | #1 | Score: 2549.8 |
| visual-question-answering-vqa-on-mmt-bench | InternVL3-78B | #1 | Accuracy: 73.2 |
| visual-question-answering-vqa-on-mtvqa | InternVL3-78B | #2 | Accuracy: 32.5 |
| zero-shot-video-question-answer-on-longvideobench | InternVL3-78B | #3 | Accuracy (% ): 65.7 |
| visual-question-answering-vqa-on-infographicvqa | InternVL3-78B | #4 | ANLS: 86.5 |
| visual-question-answering-vqa-on-mmbench-cn | InternVL3-78B | #4 | Accuracy: 88.7 |
| visual-grounding-on-refcoco-refcoco-refcocog-overall | InternVL3-78B | #5 | Accuracy: 91.4 |
| optical-character-recognition-ocr-on-ocrbench | InternVL3-78B | #6 | Score: 906 |
| visual-question-answering-vqa-on-mmbench-en | InternVL3-78B | #7 | Accuracy: 89.0 |
| chart-question-answering-on-charxiv-dq | InternVL3-78B | #8 | Accuracy: 85.1 |
| common-sense-reasoning-on-winogrande | InternVL3-78B | #8 | Accuracy: 87.8 |
| visual-question-answering-on-docvqa-test | InternVL3-78B | #8 | ANLS: 0.954 |
| visual-question-answering-vqa-on-textvqa-val | InternVL3-78B | #9 | Accuracy: 84.3 |
| vision-language-understanding-on-mmbench-v1-1 | InternVL3-78B | #10 | Accuracy: 87.7 |
| chart-question-answering-on-chartqa | InternVL3-78B | #11 | 1:1 Accuracy: 89.7 |
| video-question-answering-on-mlvu | InternVL3-78B | #12 | Accuracy: 79.5 |
| multi-task-language-understanding-on-c-eval | InternVL3-78B | #14 | Accuracy: 89.5 |
| visual-question-answering-vqa-on-blink | InternVL3-78B | #15 | Accuracy: 66.3 |
| video-question-answering-on-video-mme-with-subtitles | InternVL3-78B (w/ subtitles) | #16 | Accuracy: 75.7 |
| visual-question-answering-vqa-on-hallusionbench-average-accuracy | InternVL3-78B | #16 | Accuracy: 59.1 |
| visual-question-answering-vqa-on-realworldqa | InternVL3-78B | #16 | Accuracy: 78.0 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | InternVL3-78B | #16 | Accuracy (%): 72.7 |
| math-word-problem-solving-on-math | InternVL3-78B | #19 | Accuracy: 78.9 |
| multimodal-reasoning-on-mmmu | InternVL3-78B | #22 | Accuracy: 72.2 |
| chart-question-answering-on-charxiv-rq | InternVL3-78B | #25 | Accuracy: 46.0 |
| vision-language-understanding-on-mmstar | InternVL3-78B | #31 | Accuracy: 72.5 |
| question-answering-on-natural-questions | InternVL3-78B | #33 | EM: 39.0 |
| multimodal-reasoning-on-mathvista | InternVL3-78B | #34 | Accuracy: 79.0 |
| multimodal-reasoning-on-mathvision | InternVL3-78B | #38 | Accuracy: 43.1 |
| code-generation-on-mbpp | InternVL3-78B | #40 | Accuracy: 76.7 |
| code-generation-on-humaneval | InternVL3-78B | #52 | Pass@1: 82.3 |
| arithmetic-reasoning-on-gsm8k | InternVL3-78B | #68 | Accuracy: 90.5 |