Open Medical LLM - MMLU Professional Medicine — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 181 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | CarbonBeagle-11B-truthy | 75 |
| 2 | Llama 3 8B Instruct | 74.63 |
| 3 | Daredevil-8B-abliterated | 74.63 |
| 4 | ChimeraLlama-3-8B-v3 | 74.63 |
| 5 | NeuralLLaMa-3-8B-ORPO-v0.3 | 74.26 |
| 6 | Barcenas-Llama3-8B-ORPO | 73.9 |
| 7 | NeuralLLaMa-3-8B-DT-v0.1 | 73.53 |
| 8 | SOLAR-10.7B-Instruct-v1.0 | 73.16 |
| 9 | Sakura-SOLAR-Instruct-CarbonVillain-en-10.7B-v2-slerp | 73.16 |
| 10 | StopCarbon-10.7B-v5 | 73.16 |
| 11 | Llama 3 8B Ita | 72.79 |
| 12 | CarbonVillain-en-10.7B-v4 | 72.79 |
| 13 | Liberated-Qwen1.5-14B | 72.79 |
| 14 | Meta-Llama-3-8B-Instruct-abliterated-v3 | 72.43 |
| 15 | Llama-3-SauerkrautLM-8B-Instruct | 72.43 |
Interactive version: theaggregate.ai/benchmark?slug=open-medical-llm-mmlu-professional-medicine · How the rankings work · Data refreshed daily, snapshot 2026-07-22.