Calibration
ARC-AGI-3 → GPQA Diamond
GPQA Diamond is estimated from ARC-AGI-3 with a Michaelis–Menten curve fitted on 10 models measured on both: y = 0.9495·x / (0.00005 + x), R² = 0.72, cross-validated error 1.4 pp. It is used for 0 estimates.
GPQA Diamond is estimated from ARC-AGI-3 with a Michaelis–Menten curve fitted on 10 models measured on both: y = 0.9495·x / (0.00005 + x), R² = 0.72, cross-validated error 1.4 pp. It is used for 0 estimates.