TaichuAI has released ZDTaichu5.0-9B, a multimodal foundation model designed for visual understanding, spatial reasoning, and agentic tasks. This model integrates a Qwen3.5-9B language backbone with a C-RADIOv4-H vision encoder, capable of processing text, images, and videos with any resolution. ZDTaichu5.0-9B demonstrates strong performance in general visual understanding while also excelling in spatial reasoning and agentic capabilities compared to other models in its class. AI
IMPACT Sets new SOTA on spatial reasoning and agentic tasks for 10B-scale VLMs.
RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
Read on Hugging Face Trending Models →
- Claw-Eval
- C-RADIOv4-H
- IFEval
- MindCube-tiny
- MMSI-Bench
- Qwen3.5:9b
- SparBench
- TaichuAI
- TAU2-Bench
- ViewSpatial
- ZDTaichu5.0-9B
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →