MamaBench - Robust Accuracy: leaderboard

Metric: Robust accuracy (%; share of pairs with both the base and the counterfactual diagnosis correct; 217 expert-authored maternal and paediatric patient narratives, each paired with a minimally perturbed counterfactual whose diagnosis differs (371 pathologies); diagnoses judged by Claude Opus 4.5 at temperature 0; standalone model at temperature 0, no retrieval). Source: arxiv.org. Saturation forecast: Around August 2027. 5 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.660.8
2GPT-5.457.6
3Nemotron 3 Super47
4Kimi K2.545.6
5GLM-527.2

Interactive version: theaggregate.ai/benchmark?slug=mamabench-robust-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-29.