Calibration
Toolathlon-Verified → HLE w/ tools
HLE w/ tools is estimated from Toolathlon-Verified with a linear curve fitted on 13 models measured on both: y = 0.8269·x + -0.0279, R² = 0.79, cross-validated error 5.9 pp. It is used for 1 estimate.
| Estimated model | Toolathlon-Verified | HLE w/ tools | Source |
|---|---|---|---|
| Laguna S 2.1 | 49.7% | 38.3% | estimated ± 5.9 pp, medium confidence |