Note By Shanghai AI Lab

Note By OpenMMLab The OpenVLM Leaderboard evaluates and ranks 62 Vision-Language Models (VLMs) across 23 multi-modal benchmarks using the VLMEvalKit, featuring only open-source or publicly available API models.

Note By BAAI. The Open Chinese LLM Leaderboard aims to track, rank, and evaluate open Chinese large language models (LLMs). This leaderboard is powered by the FlagEval platform, providing corresponding computational resources and runtime environment. The evaluation dataset consists entirely of Chinese data to assess Chinese language proficiency.

Note By BAAI Featuring 50 popular closed-source models from China and beyond!

Note By Shanghai AI Lab An LLM leaderboard for Chinese models on many metric axes - super complete

Note By Tencent AI Text to video generation leaderboard

Note By Tiger Lab An arena for image generation!

Note By Alibaba - DAMO Southeast Asian (SEA) languages leaderboard

Note By Jina AI and BAAI A new benchmark focuses on fair out-of-domain evaluation for RAG & NeuralIR

Note By Tiger Lab Leaderboard for Science reasoning.

Note By Shanghai AI Lab Leaderboard for Video Generative Models.

Note By PKU-Yuan group ChronoMagic-Bench represents the inaugural benchmark dedicated to assessing T2V models' capabilities in generating time-lapse videos that demonstrate significant metamorphic amplitude and temporal coherence. The benchmark probes T2V models for their physics, biology, and chemistry capabilities, in a free-form text control.

Note TempCompass is a benchmark to evaluate the temporal perception ability of Video LLMs.

Note K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences

Note Leaderboard for LLM Safety.