AI Dynamics

Global AI News Aggregator

About

Droid Emerges Victorious as Top Benchmark Submissions Exposed as Fraudulent

every submission that was higher than droid has turned out to be fraudulent total droid victory Adam Stein (@adamlsteinl) We found widespread cheating on popular agent benchmarks, affecting 28+ submissions across 9 benchmarks and thousands of agent runs. Surprisingly, the top 3 submissions on Terminal-Bench 2 are all cheating! Here's what we found 🧵 — https://nitter.net/adamlsteinl/status/2042655187613995026#m

→ View original post on X — @scobleizer, 2026-04-11 02:12 UTC