--- id: "/tags/modality-evals-image-video-speech/page/3/" title: "Modality Evals Image Video Speech · page 3" url: "https://skillissue.dev/tags/modality-evals-image-video-speech/page/3/" --- # 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 3 of 3 - ### [SongEval](/evaluation/benchmarks-and-leaderboards/songeval/index.md) by [ASLP-lab](https://github.com/ASLP-lab) SongEval GitHub repo: song aesthetic evaluation toolkit and dataset. entity repo China en - ### [T2I-CompBench](/evaluation/benchmarks-and-leaderboards/t2i-compbench/index.md) by [Karine_H](https://github.com/Karine-Huang) T2I-CompBench GitHub repo: benchmark for compositional text-to-image generation such as attribute binding and spatial relations. entity repo China / International en - ### [T3Bench](/evaluation/benchmarks-and-leaderboards/t3bench/index.md) by [T3Bench team](https://t3bench.com/) T3Bench site: benchmark for text-to-3D generation measuring quality and alignment with the prompt. entity benchmark China / International en - ### [TTS Arena V2 (Hugging Face Space)](/evaluation/benchmarks-and-leaderboards/tts-arena-v2-hf/index.md) by [TTS AGI](https://huggingface.co/TTS-AGI) TTS Arena V2 Space: community arena voting between anonymous text-to-speech models. entity leaderboard Global (community) en - ### [UK AISI Inspect Evals](/evaluation/benchmarks-and-leaderboards/uk-aisi-inspect-evals/index.md) by [Department of Business, Energy and Industrial Strategy](https://github.com/UKGovernmentBEIS) UK AISI Inspect Evals: registry of evaluations implemented in Inspect, including cybersecurity, safety and agent benchmarks. entity benchmark UK [STATE] en|mul - ### [Vals AI MMMU Pro Leaderboard](/evaluation/benchmarks-and-leaderboards/vals-ai-mmmu-pro-archived/index.md) by [Vals AI](https://www.vals.ai/) Vals AI MMMU-Pro page: archived multimodal reasoning results and methodology; no longer run on new models. entity leaderboard US (commercial) en - ### [VBench](/evaluation/benchmarks-and-leaderboards/vbench/index.md) by [Vchitect](https://vchitect.intern-ai.org.cn/) VBench project page: benchmark suite scoring video generation models on separate quality and alignment dimensions. entity leaderboard West en - ### [VBench-2.0](/evaluation/benchmarks-and-leaderboards/vbench-2-0/index.md) by [Vchitect](https://vchitect.intern-ai.org.cn/) VBench-2.0 project page: video generation benchmark for intrinsic faithfulness, including physics and commonsense consistency. entity benchmark China / International en - ### [VBench Leaderboard (Hugging Face Space)](/evaluation/benchmarks-and-leaderboards/vbench-leaderboard-hf/index.md) by [Vchitect](https://huggingface.co/Vchitect) VBench leaderboard Space: video generation model scores across VBench dimensions, with self-submission. entity leaderboard Singapore/China en - ### [VBench / VBench++ / VBench-2.0](/evaluation/benchmarks-and-leaderboards/vbench-vbench-vbench-2-0/index.md) by [Vchitect](https://vchitect.intern-ai.org.cn/) VBench GitHub repo: evaluation suite for video generation models across many quality and consistency dimensions. entity benchmark Singapore/China (NTU S-Lab + Shanghai AI Lab per memory) en - ### [MME-Benchmarks/Video-MME](/evaluation/benchmarks-and-leaderboards/video-mme/index.md) by [MME Benchmarks](https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models) Video-MME GitHub repo: benchmark and evaluation resources for multimodal models' understanding of short to long videos. entity benchmark China; international en - ### [Video-MME](/evaluation/benchmarks-and-leaderboards/video-mme-2/index.md) by [Video-MME](https://github.com/Video-MME) Video-MME project site: benchmark for multimodal models on short, medium and long videos with subtitles and audio. entity benchmark China / International en - ### [Video-MME-v2](/evaluation/benchmarks-and-leaderboards/video-mme-v2/index.md) by [Chaoyou Fu et al.](https://orcid.org/0000-0002-0079-7668) Video-MME-v2 paper: a video-understanding benchmark with group-based consistency scoring for multimodal models. entity benchmark China en - ### [VLMEvalKit](/evaluation/benchmarks-and-leaderboards/vlmevalkit/index.md) by [OpenCompass](https://opencompass.org.cn) OpenCompass VLMEvalKit GitHub repo: evaluation toolkit for large vision-language models. entity repo China zh - ### [WorldLens](/evaluation/benchmarks-and-leaderboards/worldlens/index.md) by [worldbench](https://worldbench.github.io/worldlens) WorldLens GitHub repo (CVPR 2026): evaluations of driving world models across generation and reconstruction. entity repo Singapore / China / International en - ### [ZeroBench](/evaluation/benchmarks-and-leaderboards/zerobench/index.md) by [zerobench](https://github.com/zerobench) ZeroBench project page: visual reasoning benchmark designed so current multimodal models score near zero. entity benchmark UK (academic) en - ### [FlagEvalMM](/evaluation/benchmarks-and-leaderboards/flagevalmm/index.md) by [Zheqi He et al. (BAAI)](https://www.baai.ac.cn/) arXiv paper (2025) introducing FlagEvalMM, BAAI's framework for evaluating multimodal models. Advanced–Expert learning_resource paper China en - ### [MME](/evaluation/benchmarks-and-leaderboards/mme/index.md) by [Chaoyou Fu et al. (Nanjing University)](https://www.nju.edu.cn/) arXiv paper (2023) introducing MME, a benchmark for perception and cognition in multimodal LLMs. Advanced learning_resource paper China en - ### [SUPERB](/evaluation/benchmarks-and-leaderboards/superb/index.md) by [Shu-wen Yang et al. (National Taiwan University)](https://www.ntu.edu.tw/) arXiv paper (2021) "SUPERB: Speech processing Universal PERformance Benchmark", introducing SUPERB, a benchmark of speech representations across many speech tasks. Advanced learning_resource paper International en - ### [3D Arena paper](/evaluation/benchmarks-and-leaderboards/3d-arena-paper/index.md) by [Dylan Ebert (Hugging Face)](https://huggingface.co/) arXiv paper (2025) introducing 3D Arena, an open pairwise-preference platform for evaluating generative 3D models. Expert learning_resource paper US/France (HF) en - ### [MMMU-Pro paper](/evaluation/benchmarks-and-leaderboards/mmmu-pro-paper/index.md) by [Xiang Yue et al. (Carnegie Mellon University)](https://www.cmu.edu/) arXiv HTML version of the MMMU-Pro paper (2024), a harder multimodal multi-discipline benchmark. Expert learning_resource paper US en - ### [Open ASR Leaderboard paper](/evaluation/benchmarks-and-leaderboards/open-asr-leaderboard-paper/index.md) by [Vaibhav Srivastav et al. (Hugging Face)](https://huggingface.co/) arXiv PDF (2025) of the Open ASR Leaderboard paper: evaluation method, datasets and results for speech recognition models. Expert learning_resource paper France/UK en - ### [VBench-2.0 paper](/evaluation/benchmarks-and-leaderboards/vbench-2-0-paper/index.md) by [Dian Zheng et al. (Nanyang Technological University and Shanghai AI Laboratory)](https://www.ntu.edu.sg/) arXiv HTML version of the VBench-2.0 paper (2025) evaluating video generation on physics, commonsense and faithfulness. Expert learning_resource paper Singapore/China en [Previous page](/tags/modality-evals-image-video-speech/page/2/index.md) [Plain-text Markdown copy](/tags/modality-evals-image-video-speech/page/3/index.md)