Calibration
Vals GPQA Diamond → HLE-Verified
HLE-Verified is estimated from Vals GPQA Diamond with a offset logistic curve fitted on 6 models measured on both: y = 0.0000 + (0.5443 − 0.0000) / (1 + exp(−122.25·(x − 0.8867))), R² = 1.00, cross-validated error 4.6 pp. It is used for 8 estimates.
| Estimated model | Vals GPQA Diamond | HLE-Verified | Source |
|---|---|---|---|
| Claude Haiku 4.5 | 72.2% | 0.0% | estimated ± 4.6 pp, low confidence |
| Gemini 3.1 Flash-Lite | 81.1% | 0.0% | estimated ± 4.6 pp, low confidence |
| GLM-4.5 | 72.2% | 0.0% | estimated ± 4.6 pp, low confidence |
| Laguna M.1 | 27.0% | 0.0% | estimated ± 4.6 pp, low confidence |
| Laguna XS.2 | 55.1% | 0.0% | estimated ± 4.6 pp, low confidence |
| MiMo-V2.5 | 81.6% | 0.0% | estimated ± 4.6 pp, low confidence |
| Qwen3.5 Flash | 82.8% | 0.0% | estimated ± 4.6 pp, low confidence |
| Qwen3.8 Max | 93.7% | 54.3% | estimated ± 4.6 pp, medium confidence |