benchgap
Calibration

WideResearch → Gert Labs

Gert Labs is estimated from WideResearch with a Michaelis–Menten curve fitted on 7 models measured on both: y = 2.0000·x / (2.10623 + x), R² = 0.42, cross-validated error 6.1 pp. It is used for 5 estimates.

Estimated modelWideResearchGert LabsSource
Ornith-1.5-397B80.8%55.5%estimated ± 6.1 pp, low confidence
dots3-note Preview78.9%54.5%estimated ± 6.1 pp, low confidence
Ling 3.0 Flash73.6%51.8%estimated ± 6.1 pp, low confidence
Ornith-1.5-35B-A3B67.8%48.7%estimated ± 6.1 pp, low confidence
Ornith-1.5-9B59.5%44.1%estimated ± 6.1 pp, low confidence

Fitted on

ModelWideResearchGert Labs
Claude Opus 4.576.4%64.2%
GLM-569.8%51.0%
Kimi K2.680.8%56.8%
Kimi K2.572.7%45.9%
Qwen3.5 397B74.0%46.8%
Qwen3.6-35B-A3B60.1%42.7%
Qwen3.6 Plus74.3%50.6%