MLL Lab (Kangrui Wang, Qineng Wang, Changhe Chen et al.) · Robot Control Benchmark
Embodied First Exam
Embodied First Exam is an agent-native benchmark for testing whether coding agents can control robots under physical-world constraints. It contains 1,156 tasks across 35 suites on 47 robots, including nine new suites covering spatial puzzles, dexterous manipulation, multi-robot interaction, whole-body control and sim-to-sim engineering. The strongest of eight agents, GPT-6 Astra in Codex, reaches a 34% success rate on the 456 core tasks in the Standard Setting, and the authors also analyse where failed attempts go wrong.
Open the source ↗Similar Research & Safety releases
- One Table Benchmark
Yuanrui Wang, Kaifang Li, Xuanyue Li, Ziyun Li, Yan Lu, Xingxuan Zhang, Peng Cui (Stable AI) · Tabular Benchmark · Week 47, 2026
- MMDM: Measuring Massive Multitask Decision Making
Junhao Shen, Qing Zong, Yue Guo, Zhanqiu Zhang, Yiwen Guo, Hong Cheng (The Chinese University of Hong Kong, Database Group) · Decision model benchmark · Week 47, 2026
- Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages
Vladimir Dobrovolskii, Ibragim Badertdinov, Alexander Golubev (Nebius) · Long-tail coding benchmark · Week 47, 2026
- Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery
Shanghai AI Laboratory (Weida Wang et al.) · Metacognitive Co-Scientist · Week 47, 2026
- LongBanana
Kolors Team, Kuaishou Technology (Haoxiang Cao et al.) · Image Synthesis Benchmark · Week 47, 2026
- FinDendro: Benchmarking Temporal Self-Knowledge for Financial Backtesting
Lingfei Qian, Yan Wang, Xueqing Peng, Yupeng Cao, Yuechen Jiang, Zhuohan Xie, Anke Xu, Wenbo Cao (The Fin AI) · Temporal Knowledge Benchmark · Week 47, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.