MMLU-by-task - Electrical Engineering — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 2 70B Base | 65.52 |
| 2 | falcon-180B | 63.45 |
| 3 | StableBeluga2 | 62.76 |
| 4 | Llama 2 70B Chat | 58.62 |
| 5 | Llama 2 70B Chat (HF) | 57.93 |
| 6 | Llama 2 70B Chat GPTQ | 57.93 |
| 7 | Mistral-7B-v0.1 | 57.24 |
| 8 | LLaMA-65B | 55.86 |
| 9 | internlm-20B Chat | 55.86 |
| 10 | LLaMA-30B | 53.1 |
| 11 | Llama 2 13B Chat Base | 50.34 |
| 12 | mpt-30B | 50.34 |
| 13 | MythoMax-L2-13B | 50.34 |
| 14 | vicuna-33B-v1.3 | 50.34 |
| 15 | falcon-40B Instruct | 49.66 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-electrical-engineering · How the rankings work · Data refreshed daily, snapshot 2026-07-22.