Calibration

PostTrainBench v1.1 → AA-SciCode

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

AA-SciCode is estimated from PostTrainBench v1.1 with a Hill curve fitted on 12 models measured on both: y = 0.5538 + (1.2000 − 0.5538)·x^6.00 / (0.65486^6.00 + x^6.00), R² = 0.54, cross-validated error 3.5 pp. It is used for 1 estimate.

Estimated model	PostTrainBench v1.1	AA-SciCode	Source
Claude Opus 4.7	28.6%	55.8%	estimated ± 3.5 pp, high confidence