Llama 3 8B Slerp Biomed Chat Chinese: benchmark results
shanchen's llama3-8B-slerp-biomed-chat-chinese, a LazyMergekit SLERP merge of shanchen's biomedical Chinese Llama 3 model and Llama3-8B-Chinese-Chat. Provider: shanchen. Released 2024-04-30. Access: Open.
Aggregate Rating 1399 ± 20, rank #1209 of 1640 rated models, from 25 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Medical LLM - MedQA (USMLE) | 63.55 | Accuracy (%) | 92.2 |
| Open Medical LLM - MMLU College Medicine | 68.79 | Accuracy (%) | 88.8 |
| Open Medical LLM - MMLU Professional Medicine | 75 | Accuracy (%) | 81.8 |
| Open Medical-LLM Leaderboard (BenchmarkList) | 70.78 | Medical average (%) | 81.7 |
| Open LLM Leaderboard v1 - MMLU | 65.08 | Accuracy (%) (5-shot) | 81.4 |
| Open Medical LLM | 70.78 | Average Accuracy (%) | 81.2 |
| Open Medical LLM - MMLU Clinical Knowledge | 75.09 | Accuracy (%) | 80.5 |
| Open Medical LLM - MMLU Anatomy | 65.93 | Accuracy (%) | 71.4 |
| Open Medical LLM - PubMedQA | 75.2 | Accuracy (%) | 70.8 |
| Open Medical LLM - MedMCQA | 56.39 | Accuracy (%) | 66.7 |
| Open Medical LLM - MMLU Medical Genetics | 80 | Accuracy (%) | 66.4 |
| Open Medical LLM - MMLU College Biology | 77.08 | Accuracy (%) | 65.9 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-slerp-biomed-chat-chinese · How It Works · Data refreshed daily, snapshot 2026-11-07.