TimeSeriesExamAgent - MIMIC-IV Waveform: leaderboard

Time-series reasoning on the MIMIC-IV Waveform exam (205 questions) that TimeSeriesExamAgent (2026) generates from real data with LLM-written, LLM-verified and difficulty-filtered question templates; the series is shown as a plot. Multiple-choice accuracy in percent (chance 25); higher is better.

Metric: Accuracy (%, times 100) on the MIMIC-IV Waveform exam (205 questions): multiple-choice questions generated by TimeSeriesExamAgent from real data (Claude Sonnet 4 templates verified by gpt-4o and filtered so that gpt-4o does not score below gpt-4o-mini), time series given as plots, default API parameters; higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 5 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1TimeSeriesExamAgent Qwen2.5-VL-Instruct (checkpoint unspecified)43.9
2GPT-542.4#178
3Gemini 2.5 Pro40#276
4Gemma 3 27B (IT)37#1324
5O3 Mini35.6#546

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=timeseriesexamagent-mimic-iv-waveform · How It Works · Data refreshed daily, snapshot 2026-11-21.