benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
X / Twitter · 2026-04-09
"Prior to any official announcement from DeepSeek – at least a WeChat post – nothing that's happening is legible. They're brazenly A/B testing, changing inference settings, deploying placeholders in prod."
Teortaxes
DeepSeek V3.2
view original source →
all researcher takes →