MMLU-by-task - Moral Scenarios: leaderboard
The "Moral Scenarios" subtask of MMLU-by-task. A single MMLU subject, reporting per-task multiple-choice accuracy from the MMLU-by-task leaderboard across a wide range of academic and professional domains.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 1257 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | StableBeluga2 | 60.78 | #1078 |
| 2 | Xwin-LM-70B-V0.1 | 53.18 | #982 |
| 3 | Llama 2 70B Chat | 52.51 | #1237 |
| 4 | WizardLM-70B-V1.0 | 46.26 | #1236 |
| 5 | Llama 2 70B Base | 45.47 | #1025 |
| 6 | OpenHermes-13B | 45.14 | #1393 |
| 7 | MythoMax-L2-13B | 43.91 | #1409 |
| 8 | vicuna-33B-v1.3 | 43.58 | #1347 |
| 9 | Llama 2 70B Chat (HF) | 39.55 | #1264 |
| 10 | Chinese-Alpaca-2-13B | 38.66 | #1414 |
| 11 | trurl-2-13B-academic | 37.65 | #1413 |
| 12 | internlm-20B | 33.41 | #1296 |
| 13 | Mistral-7B-v0.1 | 32.51 | #1326 |
| 14 | falcon-40B Instruct | 32.07 | #1458 |
| 15 | Llama 2 13B Chat Base | 30.5 | #1422 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-moral-scenarios · How It Works · Data refreshed daily, snapshot 2026-10-20.