MamaBench - Base Accuracy: leaderboard

Metric: Base accuracy (%; share of pairs whose base-case diagnosis is 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 December 2026. 5 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.682
2GPT-5.477.4
3Kimi K2.576
4Nemotron 3 Super72.4
5GLM-554.8

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