MMLU-by-task - Econometrics: leaderboard
The "Econometrics" 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 | Mistral-7B-v0.1 | 50 | #1326 |
| 2 | StableBeluga2 | 46.49 | #1078 |
| 3 | Xwin-LM-70B-V0.1 | 45.61 | #982 |
| 4 | Llama 2 70B Base | 44.74 | #1025 |
| 5 | Llama 2 70B Chat | 44.74 | #1237 |
| 6 | Llama 2 70B Chat (HF) | 41.23 | #1264 |
| 7 | WizardLM-70B-V1.0 | 41.23 | #1236 |
| 8 | Vicuna-7B-v1.5-16k | 39.47 | #1491 |
| 9 | Llama 2 7B Chat | 37.72 | #1499 |
| 10 | internlm-20B | 36.84 | #1296 |
| 11 | vicuna-33B-v1.3 | 35.09 | #1347 |
| 12 | trurl-2-7B | 33.33 | #1494 |
| 13 | vicuna-13B-v1.5 | 32.46 | #1392 |
| 14 | CodeLlama-7B-Instruct-hf | 32.46 | #1545 |
| 15 | Llama 2 13B Chat Base | 31.58 | #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-econometrics · How It Works · Data refreshed daily, snapshot 2026-10-20.