Calibration

Artificial Analysis Intelligence Index → AA-Omniscience Accuracy

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

AA-Omniscience Accuracy is estimated from Artificial Analysis Intelligence Index with a offset logistic curve fitted on 183 models measured on both: y = 0.0000 + (0.6341 − 0.0000) / (1 + exp(−6.05·(x − 0.2583))), R² = 0.65, cross-validated error 7.5 pp. It is used for 4 estimates.

Estimated model	Artificial Analysis Intelligence Index	AA-Omniscience Accuracy	Source
Claude 4.1 Opus	18.6%	24.8%	estimated ± 7.5 pp, medium confidence
o1-preview	11.4%	18.7%	estimated ± 7.5 pp, medium confidence
o1-pro	12.4%	19.5%	estimated ± 7.5 pp, medium confidence
o3-pro	21.9%	27.9%	estimated ± 7.5 pp, medium confidence