benchgap
Calibration

SkillsBench → WideResearch

WideResearch is estimated from SkillsBench with a Hill curve fitted on 5 models measured on both: y = 0.2099 + (0.8356 − 0.2099)·x^6.00 / (0.33983^6.00 + x^6.00), R² = 0.93, cross-validated error 1.5 pp. It is used for 2 estimates.

Estimated modelSkillsBenchWideResearchSource
Ling 3.1 Flash68.7%82.7%estimated ± 1.5 pp, medium confidence
Muse Glimmer 30B44.3%73.0%estimated ± 1.5 pp, low confidence