Calibration
WideResearch → HLE w/ tools
HLE w/ tools is estimated from WideResearch with a offset logistic curve fitted on 6 models measured on both: y = 0.3041 + (0.5702 − 0.3041) / (1 + exp(−35.54·(x − 0.7374))), R² = 1.00, cross-validated error 2.4 pp. It is used for 9 estimates.
| Estimated model | WideResearch | HLE w/ tools | Source |
|---|---|---|---|
| Atria Dawn Preview | 81.9% | 55.6% | estimated ± 2.4 pp, medium confidence |
| Claude Opus 4.5 | 76.4% | 49.6% | estimated ± 2.4 pp, medium confidence |
| GLM-5 | 69.8% | 35.7% | estimated ± 2.4 pp, medium confidence |
| Kimi K2.6 | 80.8% | 55.0% | estimated ± 2.4 pp, medium confidence |
| Kimi K2.5 | 72.7% | 41.3% | estimated ± 2.4 pp, medium confidence |
| Ling 3.0 Flash | 73.6% | 43.4% | estimated ± 2.4 pp, medium confidence |
| Qwen3.5 397B | 74.0% | 44.3% | estimated ± 2.4 pp, medium confidence |
| Qwen3.6-35B-A3B | 60.1% | 30.6% | estimated ± 2.4 pp, medium confidence |
| Qwen3.6 Plus | 74.3% | 45.0% | estimated ± 2.4 pp, medium confidence |