Calibration

WideResearch → MCP-Tasks

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

MCP-Tasks is estimated from WideResearch with a Hill curve fitted on 5 models measured on both: y = 0.0000 + (1.1307 − 0.0000)·x^6.00 / (0.68509^6.00 + x^6.00), R² = 0.54, cross-validated error 6.0 pp. It is used for 2 estimates.

Estimated model	WideResearch	MCP-Tasks	Source
dots3-note Preview	78.9%	79.1%	estimated ± 6.0 pp, low confidence
Qwen3.8 Max	81.9%	84.2%	estimated ± 6.0 pp, low confidence