Open Medical-LLM Leaderboard (BenchmarkList): leaderboard
BenchmarkList imports the medical question-answering average over PubMedQA, MedQA, MedMCQA and six medical MMLU subjects. Some imported model labels lack the precision, repository namespace or checkpoint revision retained by the primary leaderboard. This cohort preserves the imported scores without merging those ambiguous identities into the primary results.
Metric: Medical average (%). Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 185 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 | 82.97 | #448 |
| 2 | Daredevil-8B-abliterated-dpomix | 70.99 | #843 |
| 3 | Daredevil-8B-abliterated | 70.86 | #855 |
| 4 | Llama 3 8B Slerp Biomed Chat Chinese | 70.78 | #1211 |
| 5 | NeuralLLaMa-3-8B-DT-v0.1 | 70.43 | #926 |
| 6 | NeuralLLaMa-3-8B-ORPO-v0.3 | 70.4 | #1149 |
| 7 | llama-3-merged-linear | 70.13 | #887 |
| 8 | Llama 3 8B Ita | 70.11 | #929 |
| 9 | ChimeraLlama-3-8B-v3 | 70.05 | #1059 |
| 10 | Barcenas-Llama3-8B-ORPO | 69.93 | #952 |
| 11 | Llama 3 8B | 69.9 | #1244 |
| 12 | Llama-3-SauerkrautLM-8B-Instruct | 69.76 | #896 |
| 13 | bagel-8B-v1.0 | 69.66 | #1040 |
| 14 | Llama-3-8B-Instruct-abliterated-dpomix | 69.65 | #1045 |
| 15 | suzume-llama-3-8B-multilingual | 69.3 | #1088 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-medical-llm-leaderboard-benchmarklist · How It Works · Data refreshed daily, snapshot 2026-10-24.