orpo_med_v3: benchmark results
Provider: Other. Released 2024-06-01. Access: Open.
Aggregate Rating 1421 ± 33, rank #5110 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Medical-LLM Leaderboard (BenchmarkList) | 73.94 | Medical average (%) | 96.4 |
| Open Medical LLM | 73.94 | Average Accuracy (%) | 96.1 |
| Open Medical LLM - MedMCQA | 61.3 | Accuracy (%) | 95.8 |
| Open Medical LLM - MMLU Clinical Knowledge | 78.11 | Accuracy (%) | 95.6 |
| Open Medical LLM - MMLU Professional Medicine | 79.78 | Accuracy (%) | 95.6 |
| Open Medical LLM - MMLU Anatomy | 71.85 | Accuracy (%) | 95.3 |
| Open Medical LLM - MMLU College Medicine | 71.68 | Accuracy (%) | 94.8 |
| Open Medical LLM - MMLU College Biology | 83.33 | Accuracy (%) | 93.2 |
| Open Medical LLM - MMLU Medical Genetics | 84 | Accuracy (%) | 91.4 |
| Open LLM Leaderboard v1 - MMLU | 66.63 | Accuracy (%) (5-shot) | 87.8 |
| Open Medical LLM - MedQA (USMLE) | 61.19 | Accuracy (%) | 80.7 |
| Open LLM Leaderboard v1 - GSM8K | 43.44 | Accuracy (%) (5-shot) | 57.7 |
Interactive version: theaggregate.ai/model?slug=orpo-med-v3 · How It Works · Data refreshed daily, snapshot 2026-11-08.