Calibration
ARC-AGI-2 → GPQA Diamond
GPQA Diamond is estimated from ARC-AGI-2 with a linear curve fitted on 16 models measured on both: y = 0.1198·x + 0.8398, R² = 0.66, cross-validated error 1.5 pp. It is used for 2 estimates.
| Estimated model | ARC-AGI-2 | GPQA Diamond | Source |
|---|---|---|---|
| dots3-note Preview | 81.4% | 93.7% | estimated ± 1.5 pp, high confidence |
| Gemini 3 Pro Deep Think | 45.1% | 89.4% | estimated ± 1.5 pp, high confidence |