tulu-13B-fp16: benchmark results
TheBloke's Hugging Face publication of Allen AI's Tulu 13B, whose original release is allenai/tulu-13b. Conversion publication is credited separately from the original model creator. Provider: TheBloke. Access: Open.
Aggregate Rating 1327 ± 15, rank #8224 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Econometrics | 37.72 | Accuracy (%) | 89.6 |
| MMLU-by-task - Machine Learning | 44.64 | Accuracy (%) | 88.2 |
| MMLU-by-task - High School European History | 72.12 | Accuracy (%) | 84.8 |
| MMLU-by-task - College Computer Science | 48 | Accuracy (%) | 83.8 |
| MMLU-by-task - Sociology | 75.62 | Accuracy (%) | 82.6 |
| MMLU-by-task - High School World History | 75.95 | Accuracy (%) | 80.5 |
| MMLU-by-task - Professional Accounting | 42.91 | Accuracy (%) | 80.3 |
| MMLU-by-task - Formal Logic | 37.3 | Accuracy (%) | 79.6 |
| MMLU-by-task - High School Microeconomics | 57.56 | Accuracy (%) | 79 |
| MMLU-by-task - Elementary Mathematics | 33.86 | Accuracy (%) | 78.1 |
| MMLU-by-task - College Biology | 59.72 | Accuracy (%) | 77.1 |
| MMLU-by-task - Conceptual Physics | 45.53 | Accuracy (%) | 77.1 |
Interactive version: theaggregate.ai/model?slug=tulu-13b-fp16 · How It Works · Data refreshed daily, snapshot 2026-11-08.