MMLU-by-task - Econometrics: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 1257 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral-7B-v0.1 | 50 |
| 2 | Llama 2 70B Base | 44.74 |
| 3 | Llama 2 70B Chat | 44.74 |
| 4 | Llama 2 70B Chat (HF) | 41.23 |
| 5 | Llama 2 7B Chat | 37.72 |
| 6 | LLaMA-65B | 37.72 |
| 7 | LLaMA-30B | 35.96 |
| 8 | vicuna-33B-v1.3 | 35.09 |
| 9 | trurl-2-7B | 33.33 |
| 10 | CodeLlama-7B-Instruct-hf | 32.46 |
| 11 | vicuna-13B-v1.5 | 32.46 |
| 12 | Llama 2 13B Chat Base | 31.58 |
| 13 | starcoder | 30.7 |
| 14 | ChatGLM2 6B | 30.7 |
| 15 | vicuna-13B | 29.82 |
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-econometrics · How It Works · Data refreshed daily, snapshot 2026-09-05.