Calibration

Artificial Analysis Intelligence Index → AA-GPQA Diamond

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

AA-GPQA Diamond is estimated from Artificial Analysis Intelligence Index with a Hill curve fitted on 181 models measured on both: y = 0.0000 + (0.9452 − 0.0000)·x^1.75 / (0.06219^1.75 + x^1.75), R² = 0.86, cross-validated error 6.8 pp. It is used for 5 estimates.

Estimated model	Artificial Analysis Intelligence Index	AA-GPQA Diamond	Source
Claude 4.1 Opus	18.6%	82.4%	estimated ± 6.8 pp, medium confidence
GPT-4 Turbo	7.0%	52.4%	estimated ± 6.8 pp, medium confidence
MiMo-V2.6-Flash	37.9%	90.7%	estimated ± 6.8 pp, medium confidence
MiMo-V2.6-Pro	46.3%	91.8%	estimated ± 6.8 pp, medium confidence
Mistral Large 4	38.4%	90.8%	estimated ± 6.8 pp, medium confidence