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
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 98 |
| 2 | GPT-4.1 | 79 |
| 3 | DeepSeek V3 | 72 |
| 4 | DeepSeek V2.5 | 72 |
| 5 | Gemini 2.0 Flash | 64 |
| 6 | GPT-3.5 Turbo | 6 |
Interactive version: theaggregate.ai/benchmark?slug=ehrstruct-synthea-filtering-greater-than · How It Works · Data refreshed daily, snapshot 2026-09-29.