instruct-13B: benchmark results
Provider: Other.
Aggregate Rating 1296 ± 15, rank #8801 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Chemistry | 42 | Accuracy (%) | 80.4 |
| MMLU-by-task - Econometrics | 31.58 | Accuracy (%) | 73.2 |
| MMLU-by-task - HellaSwag | 61.88 | Accuracy (%) | 71.9 |
| MMLU-by-task - Electrical Engineering | 48.97 | Accuracy (%) | 71.2 |
| MMLU-by-task - Anatomy | 48.15 | Accuracy (%) | 66.5 |
| MMLU-by-task - ARC Challenge | 54.01 | Accuracy (%) | 65.1 |
| MMLU-by-task - Machine Learning | 35.71 | Accuracy (%) | 64.2 |
| MMLU-by-task - Marketing | 76.5 | Accuracy (%) | 63.5 |
| MMLU-by-task - Logical Fallacies | 60.12 | Accuracy (%) | 63.4 |
| MMLU-by-task - Virology | 43.37 | Accuracy (%) | 62.8 |
| MMLU-by-task - High School Biology | 57.1 | Accuracy (%) | 62.6 |
| MMLU-by-task - Professional Law | 39.18 | Accuracy (%) | 62.4 |
Interactive version: theaggregate.ai/model?slug=instruct-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.