Developer Defends HLE Quality: Verified Biology Questions Show Very Few Errors
Sauers_ · x · 2026-09-02
Developer Sauers responded to doubts about the accuracy of the Humanity's Last Exam dataset, saying he personally reviewed a large number of biology questions and found the error rate to be very low (possibly just one questionable item), far from the one-third claimed by critics.
More from Research
- LagTag Chromatin Recording Work Formally Published — arjunrajlab · 2026-09-03
- SIGGRAPH Asia 2026 travel grant applications open, due September 18 — tomaszbednarz · 2026-09-03
- Planted 100 errors in papers to test AI peer review: best system caught 71, ensembles 93 — alejandroll10 · 2026-09-03
- EMNLP paper: pretraining on romanized text beats raw text for cross-lingual transfer — TuhinChakr · 2026-09-03
- HydroGym RL platform for fluid dynamics published in Nature with 60+ environments — ricardovinuesa · 2026-09-03
- Paper proposes agents that outlive their model, harness, and host by splitting identity from plumbing — omarsar0 · 2026-09-03