WiNGPT2-Llama-3-8B-Chat: benchmark results
Provider: WinGPT. Released 2024-06-01. Access: Open.
Aggregate Rating 1438 ± 46, rank #4259 of 10916 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Medical LLM - MedQA (USMLE) | 66.54 | Accuracy (%) | 93.2 |
| Open Medical LLM - MMLU Professional Medicine | 77.57 | Accuracy (%) | 85.9 |
| Open Medical LLM - MMLU Clinical Knowledge | 75.47 | Accuracy (%) | 84.1 |
| Open Medical-LLM Leaderboard (BenchmarkList) | 70.57 | Medical average (%) | 80 |
| Open Medical LLM | 70.57 | Average Accuracy (%) | 79.7 |
| Open Medical LLM - MMLU Anatomy | 66.67 | Accuracy (%) | 74.5 |
| Open Medical LLM - MMLU Medical Genetics | 81 | Accuracy (%) | 70.8 |
| Open Medical LLM - MMLU College Biology | 77.78 | Accuracy (%) | 69.3 |
| Open Chinese LLM - CMMLU | 54.89 | Accuracy (%) | 58.6 |
| Open Medical LLM - MMLU College Medicine | 63.58 | Accuracy (%) | 55.7 |
| Open Medical LLM - MedMCQA | 53.96 | Accuracy (%) | 54.7 |
| Open Chinese LLM - C-Eval Semantic | 69.34 | Accuracy (%) | 49.7 |
Interactive version: theaggregate.ai/model?slug=wingpt2-llama-3-8b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.