MMLU-by-task - Human Sexuality — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | falcon-180B | 90.08 |
| 2 | Llama 2 70B Base | 87.79 |
| 3 | StableBeluga2 | 84.73 |
| 4 | Mistral-7B-v0.1 | 79.39 |
| 5 | Llama 2 70B Chat | 77.86 |
| 6 | LLaMA-65B | 77.1 |
| 7 | vicuna-33B-v1.3 | 74.05 |
| 8 | Llama 2 70B Chat GPTQ | 73.28 |
| 9 | Llama 2 70B Chat (HF) | 70.99 |
| 10 | vicuna-13B-v1.3 | 69.47 |
| 11 | falcon-40B Instruct | 67.18 |
| 12 | internlm-20B Chat | 66.41 |
| 13 | trurl-2-13B-academic | 66.41 |
| 14 | LLaMA-30B | 65.65 |
| 15 | vicuna-13B-v1.5 | 65.65 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-human-sexuality · How the rankings work · Data refreshed daily, snapshot 2026-07-22.