Which benchmark gaps widen isn't fixed: changing the suite changes the outcome
sanmikoyejo · x · 2026-10-11
Which three gaps widen isn't fixed. Model providers invest in the skills prominent benchmarks reward; each benchmark suite rewards its own skill mix and produces its own gaps. In their runs, changing the suite changed which benchmarks widened under privacy.
More from Research
- MathEconLib open-sourced: Axiom Math and top economists bring machine-checked proofs to economics in Lean 4 — soumitrashukla9 · 2026-10-23
- Ken Ono invites the community to build MathEcon on the new Lean 4 economics library — soumitrashukla9 · 2026-10-23
- IFM open-sources RL360: 8,192 concurrent sandboxes and ~1.3M rollouts for agentic RL — rupspace · 2026-10-23
- Science lifts expression of concern on 2024 AI debunking-conspiracies paper; conclusions unchanged — DG_Rand · 2026-10-23
- Embodied First Exam benchmarks coding agents on 1,090 tasks across 44 robots — ManlingLi_ · 2026-10-23
- Anima Anandkumar on neural operators: AI weather models beat supercomputers — AnimaAnandkumar · 2026-10-23