Calibration

ARC-AGI-3 → Vals GPQA Diamond

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap

Vals GPQA Diamond is estimated from ARC-AGI-3 with a Michaelis–Menten curve fitted on 11 models measured on both: y = 0.9416·x / (0.00005 + x), R² = 0.57, cross-validated error 1.5 pp. It is used for 0 estimates.