Calibration
ARC-AGI-1 → AA-GPQA Diamond
AA-GPQA Diamond is estimated from ARC-AGI-1 with a linear curve fitted on 28 models measured on both: y = 0.2452·x + 0.6958, R² = 0.52, cross-validated error 2.7 pp. It is used for 0 estimates.
AA-GPQA Diamond is estimated from ARC-AGI-1 with a linear curve fitted on 28 models measured on both: y = 0.2452·x + 0.6958, R² = 0.52, cross-validated error 2.7 pp. It is used for 0 estimates.