Calibration
ARC-AGI-1 → GPQA
GPQA is estimated from ARC-AGI-1 with a linear curve fitted on 16 models measured on both: y = 0.2277·x + 0.7150, R² = 0.78, cross-validated error 1.7 pp. It is used for 1 estimate.
| Estimated model | ARC-AGI-1 | GPQA | Source |
|---|---|---|---|
| GPT-5.1 | 72.8% | 88.1% | estimated ± 1.7 pp, high confidence |