--- id: "/tags/modality-evals-image-video-speech/page/2/" title: "Modality Evals Image Video Speech · page 2" url: "https://skillissue.dev/tags/modality-evals-image-video-speech/page/2/" --- # Modality Evals Image Video Speech [Beginner](/levels/beginner/index.md) [Intermediate](/levels/intermediate/index.md) [Advanced](/levels/advanced/index.md) [Expert](/levels/expert/index.md) 87 resources · page 2 of 3 - ### [ImgEdit](/evaluation/benchmarks-and-leaderboards/imgedit/index.md) by [PKU-YUAN-Lab (袁粒课题组-北大深研院)](https://pku-yuan.com) ImgEdit GitHub repo from PKU: image-editing dataset and benchmark for evaluating instruction-based editing models. entity benchmark China (PKU) en - ### [KITTI Vision Benchmark Suite](/evaluation/benchmarks-and-leaderboards/kitti-vision-benchmark-suite/index.md) by [Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI)](https://www.cvlibs.net/) KITTI Vision Benchmark Suite: real driving data and leaderboards for stereo, optical flow, odometry and object detection. entity benchmark Germany / US en - ### [Arena text-to-image leaderboard](/evaluation/benchmarks-and-leaderboards/lmarena-text-to-image/index.md) by [Arena (formerly LMArena)](https://arena.ai/) Arena (formerly LMArena) text-to-image leaderboard: human-preference rankings of image generation models. entity leaderboard US en - ### [Arena text-to-video leaderboard](/evaluation/benchmarks-and-leaderboards/lmarena-text-to-video/index.md) by [Arena (formerly LMArena)](https://arena.ai/) Arena (formerly LMArena) text-to-video leaderboard: human-preference rankings of video generation models. entity leaderboard US en - ### [LMMS-Eval](/evaluation/benchmarks-and-leaderboards/lmms-eval/index.md) by [LMMs-Lab](https://github.com/EvolvingLMMs-Lab) LMMS-Eval GitHub repo: evaluation toolkit for multimodal models across text, image, video and audio tasks. entity repo International en - ### [Probing the limitations of multimodal language models for chemistry and materials research (MaCBench)](/evaluation/benchmarks-and-leaderboards/macbench-multimodal-chemistry-materials/index.md) by [Nawaf Alampara et al. (Friedrich Schiller University Jena)](https://www.uni-jena.de/en) MaCBench paper probing multimodal language models on chemistry and materials-science tasks such as reading spectra and lab images. entity benchmark Germany en - ### [MathVision](/evaluation/benchmarks-and-leaderboards/mathvision/index.md) by [LLMs for Reasoning](https://github.com/mathllm) MATH-Vision project page: competition math problems with visual contexts for evaluating multimodal reasoning. entity benchmark China / International en - ### [MathVista](/evaluation/benchmarks-and-leaderboards/mathvista/index.md) by [mathvista](https://mathvista.github.io/) MathVista project page: benchmark of math reasoning in visual contexts such as charts, diagrams and figures. entity benchmark US / International en - ### [MERA Multimodal](/evaluation/benchmarks-and-leaderboards/mera-multimodal/index.md) by [MERA Evaluation](https://mera.a-ai.ru/) MERA Multimodal GitHub repo: open benchmark for evaluating multimodal models in Russian, with task definitions and code. entity benchmark Russia ru - ### [MMAU](/evaluation/benchmarks-and-leaderboards/mmau/index.md) by [mmaubench](https://github.com/mmaubench) MMAU project page: audio understanding and reasoning benchmark over speech, music and environmental sounds. entity benchmark International en - ### [MMAU-Pro](/evaluation/benchmarks-and-leaderboards/mmau-pro/index.md) by [Sonal Kumar](https://github.com/sonalkum) MMAU-Pro GitHub repo: benchmark for audio understanding and reasoning in audio-language models. entity repo International en - ### [MMBench](/evaluation/benchmarks-and-leaderboards/mmbench/index.md) by [OpenCompass](https://opencompass.org.cn) OpenCompass MMBench GitHub repo: multimodal evaluation benchmark in multiple languages. entity repo China zh - ### [MMMU](/evaluation/benchmarks-and-leaderboards/mmmu/index.md) by [MMMU](https://github.com/MMMU-Benchmark) MMMU project site: college-level multimodal reasoning benchmark across disciplines, including MMMU-Pro and leaderboards. entity benchmark US / International en - ### [MTEB Leaderboard](/evaluation/benchmarks-and-leaderboards/mteb/index.md) by [Massive Text Embedding Benchmark](https://huggingface.co/mteb) MTEB leaderboard Space: embedding model scores across many retrieval, clustering and classification tasks. entity leaderboard West mul - ### [MuChoMusic](/evaluation/benchmarks-and-leaderboards/muchomusic/index.md) by [MuLaB](https://github.com/mulab-mir) MuChoMusic GitHub repo: benchmark for music understanding in audio language models. entity repo Germany / International en - ### [MusTBench](/evaluation/benchmarks-and-leaderboards/mustbench/index.md) by [Sony](https://www.sony.com/en/) Sony MusTBench GitHub repo: benchmark for temporal grounding of music in large audio-language models. entity repo Japan / International en - ### [MVBench (OpenGVLab/Ask-Anything)](/evaluation/benchmarks-and-leaderboards/mvbench/index.md) by [OpenGVLab](https://github.com/OpenGVLab) OpenGVLab Ask-Anything GitHub repo: VideoChat models and the MVBench video understanding benchmark. entity repo China en - ### [nuScenes](/evaluation/benchmarks-and-leaderboards/nuscenes/index.md) by [Motional (nuScenes)](https://www.nuscenes.org/) nuScenes site: autonomous-driving dataset with camera, lidar and radar data plus detection, tracking and prediction benchmarks. entity benchmark US / Singapore en - ### [ObjectNet](/evaluation/benchmarks-and-leaderboards/objectnet/index.md) by [ObjectNet team (MIT)](https://objectnet.dev/) ObjectNet site: real-world object recognition test set with controlled backgrounds, rotations and viewpoints. entity benchmark US en - ### [OCRBench](/evaluation/benchmarks-and-leaderboards/ocrbench/index.md) by [Yuliang Liu](https://github.com/Yuliang-Liu) MultimodalOCR GitHub repo: OCRBench evaluation of text recognition in large multimodal models. entity repo China / International en - ### [OmniDocBench](/evaluation/benchmarks-and-leaderboards/omnidocbench/index.md) by [OpenDataLab](https://opendatalab.org.cn) OmniDocBench GitHub repo: benchmark for document parsing covering layout, tables, formulas and OCR across document types. entity benchmark China zh - ### [Open ASR Leaderboard](/evaluation/benchmarks-and-leaderboards/open-asr-leaderboard/index.md) by [Hugging Face for Audio](https://huggingface.co/hf-audio) Hugging Face Open ASR Leaderboard: word error rate and speed of speech recognition models on public datasets. entity leaderboard West en|mul - ### [Open VLM Leaderboard (OpenCompass)](/evaluation/benchmarks-and-leaderboards/open-vlm-leaderboard-opencompass/index.md) by [OpenCompass](https://huggingface.co/opencompass) OpenCompass Open VLM Leaderboard Space: vision-language model results aggregated from VLMEvalKit benchmarks. entity leaderboard West en|zh - ### [OpenCompass](/evaluation/benchmarks-and-leaderboards/opencompass-2/index.md) by [OpenCompass](https://opencompass.org.cn) OpenCompass GitHub repo: LLM evaluation platform with configs for many datasets, inference, judging and leaderboards. entity benchmark China zh - ### [OpenCompass CompassRank: Multimodal Leaderboard](/evaluation/benchmarks-and-leaderboards/opencompass-compassrank-multimodal/index.md) by [Shanghai AI Laboratory (OpenCompass)](https://opencompass.org.cn/) OpenCompass CompassRank multimodal leaderboard: scores of vision-language models across benchmarks. entity leaderboard China [STATE] zh - ### [P3D-Bench](/evaluation/benchmarks-and-leaderboards/p3d-bench/index.md) by [SpatiaOS](https://github.com/SpatiaOS) P3D-Bench GitHub repo: benchmark of MLLMs on parametric 3D generation and structural reasoning. entity repo International en - ### [PhysBench](/evaluation/benchmarks-and-leaderboards/physbench/index.md) by [PhysBench](https://github.com/PhysBench) PhysBench project page: benchmark of physical-world questions testing vision-language models on objects, motion and interactions. entity benchmark International en - ### [POPE](/evaluation/benchmarks-and-leaderboards/pope/index.md) by [Yifan Li](https://github.com/AoiDragon) POPE GitHub repo (EMNLP 2023): polling-based evaluation of object hallucination in vision-language models. entity repo China en - ### [Rapidata Image-to-3D](/evaluation/benchmarks-and-leaderboards/rapidata-image-to-3d/index.md) by [Rapidata](https://www.rapidata.ai/) benchmark.ai Image-to-3D leaderboard from Rapidata ranking 3D generation models by pairwise human preference votes. entity benchmark Switzerland / Global en - ### [ScanNet benchmark](/evaluation/benchmarks-and-leaderboards/scannet-benchmark/index.md) by [ScanNet](https://github.com/ScanNet) ScanNet GitHub repo: RGB-D video dataset of 1,500+ indoor scans with 3D annotations and benchmark. entity repo US / International en - ### [SEED-TTS-EVAL](/evaluation/benchmarks-and-leaderboards/seed-tts-eval/index.md) by [BytedanceSpeech](https://github.com/BytedanceSpeech) ByteDance seed-tts-eval GitHub repo: objective test set and scripts for evaluating TTS models. entity repo China en - ### [SongBench](/evaluation/benchmarks-and-leaderboards/songbench/index.md) by [Tencent](https://opensource.tencent.com) Tencent SongBench GitHub repo: benchmark evaluating AI-generated songs across multiple musical dimensions. entity repo China en [Previous page](/tags/modality-evals-image-video-speech/index.md) [Next page](/tags/modality-evals-image-video-speech/page/3/index.md) [Plain-text Markdown copy](/tags/modality-evals-image-video-speech/page/2/index.md)