https://hyper.ai/en/sota/tasks/common-sense-reasoning/benchmark/codah 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/common-sense-reasoning/benchmark/visual-dialog-v0-9 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/common-sense-reasoning/benchmark/visual-dialog-v0-9-1 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/common-sense-reasoning/benchmark/winogavil 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/common-sense-reasoning/benchmark/Real-World Web 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/common-sense-reasoning/benchmark/QASC 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/common-sense-reasoning/benchmark/openbookqa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/common-sense-reasoning/benchmark/arc 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/common-sense-reasoning/benchmark/ALFWorld 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/activitynet-qa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/msrvtt-qa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/msvd-qa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/egoschema-fullset 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/next-qa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/tgif-qa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/egoschema-subset 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/intentqa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/VideoMME 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/video-mme 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/tvqa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/video-mme-w-o-subs 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/next-gqa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/zero-shot-video-question-answering-on 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/situated-reasoning-star 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/mvbench 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/MovieChat-1k 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/cinepile 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/K700 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/K600 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/K400 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/VideoAds 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/zeroshot-video-question-answer/benchmark/AdsQA 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/rebus 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/math-v 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/MM-Verify 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/MathVista 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/FCMR 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/SCIVER 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/algopuzzlevqa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/MathVision 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/Yo'LLaVA 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/R1-Onevision-Bench 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/PerVA 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/MyVLM 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/MMAT-1M 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/MM-Reasoner 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/MathVerse 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/LLaVA-CoT 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/INS-MMBench 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/Geo170K 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/FinMMR 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/FINMME 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/DriveQA 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/multimodal-reasoning/benchmark/BDD-OIA 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/math 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/mawps 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/svamp 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/math23k 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/alg514 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/asdiv-a 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/paramawps 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/draw-1k 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/mathqa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/svamp-1-n 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/gsm8k 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/math-minival 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/pen 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/hellaswag 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/gsm-plus 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/piqa 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/CSQA 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/math-word-problem-solving/benchmark/winogrande 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/winoground 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/nlvr2-dev 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/nlvr2-test 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/clevrer 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/bongard-openworld 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/winogavil 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/vsr 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/phyre-1b-within 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/phyre-1b-cross 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/vasr 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/nlvr 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/irfl-image-recognition-of-figurative-language 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/What'sUp 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/COMFORT++ 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/elevater 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/3DSRBench 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/sDCI 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/visual-reasoning/benchmark/ARO 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/3d-human-reconstruction 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/3d-human-reconstruction/benchmark/4d-dress 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/3d-human-reconstruction/benchmark/customhumans 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/3d-human-reconstruction/benchmark/agora 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/3d-human-reconstruction/benchmark/expressive-hands-and-faces-dataset-ehf-1 2026-07-09T07:23:29.715Z https://hyper.ai/en/sota/tasks/3d-human-reconstruction/benchmark/cape 2026-07-09T07:23:29.715Z