A transparent real-world autonomous-agent benchmark with 300 human-verified tasks, 2,159 rubric items, and Pass^3 scoring across general, multi-turn, and native multimodal agent tasks.
Bowen Ye, Rang Li, Qibin Yang, Yuanxin Liu, Linli Yao, Hanglong Lv, Zhihui Xie, Chenxin An, Lei Li, Lingpeng Kong, Qi Liu, Zhifang Sui, Tong Yang
Category
Agents
Version
2026
Direction
higher is better
Ranking use
Reference
Contamination risk
Unknown
A transparent real-world autonomous-agent benchmark with 300 human-verified tasks, 2,159 rubric items, and Pass^3 scoring across general, multi-turn, and native multimodal agent tasks. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
A transparent real-world autonomous-agent benchmark with 300 human-verified tasks, 2,159 rubric items, and Pass^3 scoring across general, multi-turn, and native multimodal agent tasks.
Which model scores highest on Claw-Eval?
Ornith-1.0-397B by DeepReinforce AI currently leads with 77.1%.
How many models are evaluated on Claw-Eval?
33 models in the LuminaBench cohort have a qualifying score on this benchmark.
