Calibration
SuperGPQA → GPQA
GPQA is estimated from SuperGPQA with a Hill curve fitted on 15 models measured on both: y = 0.0000 + (0.9370 − 0.0000)·x^6.00 / (0.44470^6.00 + x^6.00), R² = 0.65, cross-validated error 2.6 pp. It is used for 3 estimates.
| Estimated model | SuperGPQA | GPQA | Source |
|---|---|---|---|
| Qwen 3.6 Max (preview) | 73.9% | 89.4% | estimated ± 2.6 pp, high confidence |
| Seed 2.1 Pro | 70.8% | 88.3% | estimated ± 2.6 pp, high confidence |
| Seed 2.1 Turbo | 67.4% | 86.6% | estimated ± 2.6 pp, high confidence |