Calibration
WideResearch → Toolathlon-Verified
Toolathlon-Verified is estimated from WideResearch with a inverse Michaelis–Menten curve fitted on 6 models measured on both: y = 0.64122·(x − 0.0000) / (0.0000 + 1.5727 − x), R² = 0.89, cross-validated error 5.5 pp. It is used for 1 estimate.
| Estimated model | WideResearch | Toolathlon-Verified | Source |
|---|---|---|---|
| Qwen3.5 397B | 74.0% | 57.0% | estimated ± 5.5 pp, low confidence |