Calibration

LABBench2 → Vals GPQA Diamond

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

Vals GPQA Diamond is estimated from LABBench2 with a Michaelis–Menten curve fitted on 6 models measured on both: y = 2.0000·x / (0.95480 + x), R² = 0.43, cross-validated error 2.2 pp. It is used for 1 estimate.

Estimated model	LABBench2	Vals GPQA Diamond	Source
Gemini 4 Argon	88.8%	96.4%	estimated ± 2.2 pp, low confidence