Calibration
SuperGPQA → HLE
HLE is estimated from SuperGPQA with a linear curve fitted on 12 models measured on both: y = 0.7717·x + -0.2155, R² = 0.68, cross-validated error 7.8 pp. It is used for 7 estimates.
| Estimated model | SuperGPQA | HLE | Source |
|---|---|---|---|
| Qwen3 235B 2507 | 62.6% | 26.8% | estimated ± 7.8 pp, medium confidence |
| Qwen3.5-122B-A10B | 67.1% | 30.2% | estimated ± 7.8 pp, medium confidence |
| Qwen3.5-27B | 65.6% | 29.1% | estimated ± 7.8 pp, medium confidence |
| Qwen3.5-35B-A3B | 63.4% | 27.4% | estimated ± 7.8 pp, medium confidence |
| Qwen 3.6 Max (preview) | 73.9% | 35.5% | estimated ± 7.8 pp, medium confidence |
| Seed 2.1 Pro | 70.8% | 33.1% | estimated ± 7.8 pp, medium confidence |
| Seed 2.1 Turbo | 67.4% | 30.5% | estimated ± 7.8 pp, medium confidence |