Observation record / arXiv · 人工智能

GardenBench: A lightweight, daily evaluation of LLM capabilities

First seen 10/20, 12:53 · Last observed 10/21, 06:54 · Source data is current

Title-based outlineGardenBench: A lightweight, daily evaluation of LLM capabilities

Why it mattersResearch metadata links to papers and authors. Read the original for conclusions; publication order is not impact.

Published 10/20, 12:00

30 minutesRank movement—

Building history

1 hourRank movement—

Building history

24 hoursRank movement—

Building history

Publication position history

4 observations

Publication feed in source order. Position changes do not count as heat or momentum.

arXiv metadata CC0; papers retain individual licenses· Author Benedict Cummins-Mburu, Mariana Garcia Mejia, Oscar Heath, Sabrina Kreyzerman, Ellie Murray, Arusan

View original observation times and ranks

Observation time (Beijing)	Source position
10/21, 06:54	1
10/21, 00:54	1
10/20, 18:54	1
10/20, 12:53	1

Daily aggregate history

日期	Best daily position	Last daily position	Observations
2026-10-20	1	1	2
2026-10-21	1	1	2