MMLU-by-task - High School Microeconomics — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | StableBeluga2 | 81.09 |
| 2 | falcon-180B | 77.73 |
| 3 | Llama 2 70B Base | 76.47 |
| 4 | Llama 2 70B Chat | 76.47 |
| 5 | LLaMA-65B | 68.07 |
| 6 | Llama 2 70B Chat (HF) | 65.97 |
| 7 | Mistral-7B-v0.1 | 65.97 |
| 8 | Llama 2 70B Chat GPTQ | 65.97 |
| 9 | vicuna-33B-v1.3 | 59.24 |
| 10 | OpenHermes-13B | 59.24 |
| 11 | vicuna-13B-v1.5 | 58.4 |
| 12 | WizardLM-13B-V1.2 | 57.98 |
| 13 | LLaMA-30B | 57.56 |
| 14 | MythoMax-L2-13B | 57.56 |
| 15 | falcon-40B Instruct | 57.14 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-high-school-microeconomics · How the rankings work · Data refreshed daily, snapshot 2026-07-22.