SweetBench Pro
product
3 mentions
3 recordings
first heard Feb 2026
last heard 10 Jul
±0 this week
OpenAI benchmark that was found to contain many broken tasks
Trend
No mentions in the last 7d.Widen the range to see when SweetBench Pro was said.
Moments
newest first · ▶ plays the momentNathaniel WhittemoreThe AI Daily Brief: Artificial Intelligence News and Analysis · ChatGPT Just Became a Work Agent · 1:51 · 10 Jul
…In a new report, OpenAI audited SweeBench Pro and found the benchmark to be sorely lacking.…
Sebastian RaschkaLatent Space: The AI Engineer Podcast · [LIVE] Anthropic Distillation & How Models Cheat (SWE-Bench ... · 43:48 · 26 Feb
…I think there is like a Sweetbench Pro now, which is kind of like uh…
Olivia WatkinsLatent Space: The AI Engineer Podcast · ⚡️The End of SWE-Bench Verified — Mia Glaese & Olivia ... · 1:29 · 23 Feb
…Like Super Red Pro.…
All 3 moments