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
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11