Author Claims Benchmark Remains Uncontaminated

Afinetheorem · x · 2026-07-11

The author added that they have a "neat trick" to determine if this benchmark has been absorbed into the models' training data, though they don't plan to reveal it yet.

Based on current observations: this benchmark hasn't been significantly contaminated, meaning there's no evidence that models have already learned these questions through ingest.

Original post →

More from Research

Research channel →