benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
YouTube · 2026-04-10
"Agents could do about 20 steps by the end of last year. GLM 5.1 can do 1,700 right now. Autonomous work time may be the most important curve after scaling laws."
Lu
Z.ai Leader
GLM-5.1
view original source →
all researcher takes →