Calibration

Toolathlon → WideResearch

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap

WideResearch is estimated from Toolathlon with a linear curve fitted on 7 models measured on both: y = 0.6351·x + 0.4879, R² = 0.65, cross-validated error 5.6 pp. It is used for 1 estimate.

Estimated model	Toolathlon	WideResearch	Source
MiniMax M2.7	46.3%	78.2%	estimated ± 5.6 pp, low confidence