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...

Open Medical LLM - MMLU College Medicine — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 181 models tracked.

Top models

#ModelScore
1Liberated-Qwen1.5-14B68.21
2Yi-1.5-9B67.63
3Yi-1.5-9B-32K67.63
4NeuralLLaMa-3-8B-DT-v0.166.47
5suzume-llama-3-8B-multilingual65.9
6Meta-Llama-3-8B-Instruct-abliterated-v365.9
7CarbonBeagle-11B-truthy65.9
8Llama 3 8B Instruct65.32
9Starling-LM-7B-beta65.32
10SOLAR-10.7B-Instruct-v1.065.32
11Daredevil-8B-abliterated65.32
12NeuralLLaMa-3-8B-ORPO-v0.365.32
13CarbonVillain-en-10.7B-v465.32
14Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp65.32
15StopCarbon-10.7B-v565.32

Interactive version: theaggregate.ai/benchmark?slug=open-medical-llm-mmlu-college-medicine · 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.