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 Professional Medicine — leaderboard

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

Top models

#ModelScore
1CarbonBeagle-11B-truthy75
2Llama 3 8B Instruct74.63
3Daredevil-8B-abliterated74.63
4ChimeraLlama-3-8B-v374.63
5NeuralLLaMa-3-8B-ORPO-v0.374.26
6Barcenas-Llama3-8B-ORPO73.9
7NeuralLLaMa-3-8B-DT-v0.173.53
8SOLAR-10.7B-Instruct-v1.073.16
9Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp73.16
10StopCarbon-10.7B-v573.16
11Llama 3 8B Ita72.79
12CarbonVillain-en-10.7B-v472.79
13Liberated-Qwen1.5-14B72.79
14Meta-Llama-3-8B-Instruct-abliterated-v372.43
15Llama-3-SauerkrautLM-8B-Instruct72.43

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