MMLU-by-task - Human Aging — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | falcon-180B | 83.41 |
| 2 | Llama 2 70B Base | 80.27 |
| 3 | Llama 2 70B Chat | 79.37 |
| 4 | StableBeluga2 | 78.03 |
| 5 | Llama 2 70B Chat (HF) | 72.65 |
| 6 | Mistral-7B-v0.1 | 70.4 |
| 7 | Llama 2 70B Chat GPTQ | 70.4 |
| 8 | MythoMax-L2-13B | 68.61 |
| 9 | LLaMA-30B | 67.71 |
| 10 | LLaMA-65B | 66.37 |
| 11 | OpenHermes-13B | 66.37 |
| 12 | falcon-40B Instruct | 65.92 |
| 13 | vicuna-13B-v1.5 | 65.92 |
| 14 | vicuna-33B-v1.3 | 65.47 |
| 15 | internlm-20B Chat | 65.47 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-human-aging · How the rankings work · Data refreshed daily, snapshot 2026-07-22.