MMLU Professional Medicine (Open Medical-LLM)
Science · 2024-04-19
The professional-medicine subset of MMLU, 272 questions, scored by the Open Medical-LLM Leaderboard under lm-evaluation-harness with a fixed prompt.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-4 | 93.8 |
| Llama 3 8B Instruct | 74.6 |
| Solar 10.7B Instruct V1.0 | 73.2 |
| GPT-3.5 Turbo 1106 | 72.8 |
| Llama 3 8B | 70.2 |
| Mistral 7B v0.1 Base | 68.4 |
| Qwen1.5 7B Chat | 65.4 |
| Zephyr 7B Beta | 65.4 |
| Gemma 7B | 63.2 |
| Mistral 7B Instruct v0.1 | 59.6 |
| Qwen1.5 7B | 59.6 |
| Gemma 1.1 7B IT | 54.0 |
| Gemma 7B IT | 47.1 |
| Phi-1.5 | 29.0 |
| Gemma 2B | 18.0 |
| Falcon 7B | 17.6 |