Zhiyuan GO-3 Nano Preview Tops RoboDojo Evaluation
The story so far
Zhiyuan's product GO-3 Nano Preview achieved an average score of 61.90 and a success rate of 56.42% in the RoboDojo evaluation, topping the list and surpassing GPT-6 Astra. It also ranked first in three sub-dimensions: fine manipulation, long-range execution, and open semantic understanding. This result was disclosed by the embodied intelligence evaluation benchmark RoboDojo on October 27, 2026. Additionally, the uni-robot-agent framework equipped with Qwen3.8-Flash-Next also performed excellently in the RoboDojo evaluation, scoring 31.39 and surpassing GPT-6 Astra-RoboProbe and many VLA/WAM baselines.
AI-written from the reports · Updated 16 days ago
Developments
2 developments
- 3 Nov, 08:00 · 1 reportsDemocratizing Robot-Use AgentsHugging Face Daily Papers:Democratizing Robot-Use Agents: A Unified Harness with Open Models
- 27 Oct, 14:03 · 1 reportsReached the top of RoboDojo36Kr · AI:Zhiyuan GO-3 Nano Preview Tops RoboDojo Review Rankings
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersDemocratizing Robot-Use Agents: A Unified Harness with Open Models
The uni-robot-agent framework enables open-source weight robots to surpass proprietary models using agents in zero-shot operation, with its onboard Qwen3.8-Flash-Next scoring 31.39 in the RoboDojo evaluation, exceeding GPT-6 Astra-RoboProbe's 28.97 score and numerous VLA/WAM baselines, and performing excellently in 19 real tasks. Analysis indicates that effective robot use requires combining four general capabilities, suggesting future training should synergistically develop these capabilities.
- 36Kr · AIZhiyuan GO-3 Nano Preview Tops RoboDojo Review Rankings
Zhiyuan GO-3 Nano Preview tops RoboDojo evaluation with an average score of 61.90 and a success rate of 56.42%, surpassing GPT-6 Astra, and ranking first in fine manipulation, long-range execution, and open semantic understanding across three sub-dimensions.