Calibration
GPQA → ARC-AGI-1
ARC-AGI-1 is estimated from GPQA with a linear curve fitted on 16 models measured on both: y = 3.4467·x + -2.2763, R² = 0.79, cross-validated error 6.9 pp. It is used for 3 estimates.
| Estimated model | GPQA | ARC-AGI-1 | Source |
|---|---|---|---|
| Claude 3.5 Sonnet | 59.4% | 0.0% | estimated ± 6.9 pp, low confidence |
| LFM2.5-VL-450M | 25.7% | 0.0% | estimated ± 6.9 pp, low confidence |
| Qwen3 235B 2507 | 77.5% | 39.5% | estimated ± 6.9 pp, low confidence |