tulu-30B-fp16: benchmark results
TheBloke's Hugging Face publication of Allen AI's Tulu 30B, whose original release is allenai/tulu-30b. Conversion publication is credited separately from the original model creator. Provider: TheBloke. Access: Open.
Aggregate Rating 1353 ± 15, rank #7624 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School European History | 77.58 | Accuracy (%) | 90.7 |
| MMLU-by-task - High School World History | 81.86 | Accuracy (%) | 90 |
| MMLU-by-task - High School US History | 82.35 | Accuracy (%) | 89.5 |
| MMLU-by-task - High School Psychology | 78.9 | Accuracy (%) | 87.8 |
| MMLU-by-task - Marketing | 85.04 | Accuracy (%) | 87.7 |
| MMLU-by-task - Professional Accounting | 46.1 | Accuracy (%) | 87.1 |
| MMLU-by-task - Professional Medicine | 58.09 | Accuracy (%) | 87 |
| MMLU-by-task - World Religions | 79.53 | Accuracy (%) | 86.4 |
| MMLU-by-task - Virology | 48.8 | Accuracy (%) | 86 |
| MMLU-by-task - Jurisprudence | 74.07 | Accuracy (%) | 85.9 |
| MMLU-by-task - Logical Fallacies | 69.94 | Accuracy (%) | 85.8 |
| MMLU-by-task - Public Relations | 66.36 | Accuracy (%) | 85.5 |
Interactive version: theaggregate.ai/model?slug=tulu-30b-fp16 · How It Works · Data refreshed daily, snapshot 2026-11-08.