Calibration
WideResearch → HLE w/ tools
HLE w/ tools is estimated from WideResearch with a linear curve fitted on 7 models measured on both: y = 1.1150·x + -0.3544, R² = 0.84, cross-validated error 5.3 pp. It is used for 4 estimates.
| Estimated model | WideResearch | HLE w/ tools | Source |
|---|---|---|---|
| Qwen3.6 Plus | 74.3% | 47.4% | estimated ± 5.3 pp, low confidence |
| Qwen3.5 397B | 74.0% | 47.1% | estimated ± 5.3 pp, low confidence |
| Ling 3.0 Flash | 73.6% | 46.6% | estimated ± 5.3 pp, low confidence |
| Qwen3.6-35B-A3B | 60.1% | 31.6% | estimated ± 5.3 pp, low confidence |