EHRStruct (Synthea) - Filtering (Greater Than): leaderboard

Metric: Accuracy (%; D-U1: 100 zero-shot questions on synthetic Synthea patient tables given as plain text, where each item asks to list the IDs of the patients meeting a condition on a categorical field and a greater-than condition on a numeric field; an answer counts when it matches the reference exactly; the paper's check mark, a perfect score, reads 100, and its cross, no valid output, reads as missing). Source: arxiv.org. Saturation forecast: Estimated already saturated. 17 models tracked.

Top models

#ModelScore
1Gemini 2.5 Flash98
2GPT-4.179
3DeepSeek V372
4DeepSeek V2.572
5Gemini 2.0 Flash64
6GPT-3.5 Turbo6

Interactive version: theaggregate.ai/benchmark?slug=ehrstruct-synthea-filtering-greater-than · How It Works · Data refreshed daily, snapshot 2026-09-29.