Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

PubMedQA — leaderboard

Biomedical research question-answering benchmark requiring yes/no/maybe answers from PubMed abstracts with expert-labeled and generated splits.

Metric: Accuracy (%). Source: pubmedqa.github.io. 24 models tracked.

Top models

#ModelScore
1GPT-482
2GPT-3.579.6
3Median Human65

Interactive version: theaggregate.ai/benchmark?slug=pubmedqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.