Grok 4.5 Benchmarks Tainted by Training Data
SkyLi0n · x · 2026-07-10
A post suggests that Grok 4.5's edge on CursorBench is partly due to its training data accidentally containing an early snapshot of the Cursor codebase.
The author added that this batch of data has been removed, ensuring subsequent models will not have the same issue.
Related event: Grok 4.5 Benchmarks Strong but Faces Data Controversy(6 posts)→
More from Models
- Open-source labs could distill a state-of-the-art model to 32GB or 80GB VRAM, the post argues — bookwormengr · 2026-07-21
- Moonshot pauses Kimi K3 signups five days after launch as GPU demand surges — eyishazyer · 2026-07-21
- AI Diplomacy demo makes agents negotiate, ally, and betray each other — jamdac · 2026-07-21
- Newer models need a different prompting style, and old tricks can make outputs worse — emollick · 2026-07-21
- GLM-5.5 is said to arrive in 4 weeks with open weights — tanay_mehta · 2026-07-21
- Fable 5 is credited with a 3-variable counterexample to the Jacobian conjecture — Various-Affect4841 · 2026-07-21