Open Chinese LLM Leaderboard
Explore and submit LLM benchmarks
None defined yet.
OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale
EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models
Explore and submit LLM benchmarks
FlagEval VLM Leaderboard
Compare and evaluate language models side-by-side
URSA Text-to-Image-to-Video
Open Veo3-style Audio-Video Generation
Search for information using keywords
Leaderboard for MVRB (Massive Visualized IR Benchmark)
Segment and caption objects in images
Generate images and answer questions using text input
Generate and chat using multimodal inputs
Segment 3D medical images using prompts
Generate images from text prompts
Generate images from text prompts
Segment objects in images and videos with a single touch