Llama3-OpenBioLLM-8B: benchmark results
Provider: Meta. Released 2024-05-01. Access: Open.
Aggregate Rating 1389 ± 25, rank #6575 of 10916 rated models, from 57 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MedConceal (Adaptive) - Confirmation Coarse F1 | 68.8 | Coarse-grained F1 (0-1, times 100) of the concern categories | 100 |
| MedConceal (Adaptive) - Confirmation Reveal Rate | 94.4 | Reveal rate (0-1, times 100): share of the gold hidden conce | 100 |
| Open Medical LLM - MMLU College Biology | 83.33 | Accuracy (%) | 93.2 |
| Open Medical LLM - MMLU Medical Genetics | 84 | Accuracy (%) | 91.4 |
| Open Medical LLM - MMLU Clinical Knowledge | 76.6 | Accuracy (%) | 90.1 |
| Open Medical LLM - MMLU Professional Medicine | 78.31 | Accuracy (%) | 88.8 |
| Open Medical-LLM Leaderboard (BenchmarkList) | 71.73 | Medical average (%) | 88.3 |
| Open Medical LLM | 71.73 | Average Accuracy (%) | 87.5 |
| Open Medical LLM - MedMCQA | 57.76 | Accuracy (%) | 86.7 |
| Open Medical LLM - MMLU College Medicine | 67.63 | Accuracy (%) | 84.6 |
| Open Medical LLM - MMLU Anatomy | 68.15 | Accuracy (%) | 78.1 |
| MedConceal (8-Turn) - Confirmation Reveal Rate | 52 | Reveal rate (0-1, times 100): share of the gold hidden conce | 75 |
Interactive version: theaggregate.ai/model?slug=llama3-openbiollm-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.