mpt-30B Instruct: benchmark results
Provider: Databricks. Released 2023-06-22. Access: Open.
Unified ELO 1363 ± 1, rank #1234 of 1392 rated models, from 74 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Mathematics | 32.96 | Accuracy (%) | 91.8 |
| MMLU-by-task - HellaSwag | 65.25 | Accuracy (%) | 89.8 |
| MMLU-by-task - College Physics | 35.29 | Accuracy (%) | 88.7 |
| MMLU-by-task - College Computer Science | 47 | Accuracy (%) | 79.9 |
| MMLU-by-task - Conceptual Physics | 46.38 | Accuracy (%) | 79.4 |
| MMLU-by-task - Virology | 46.39 | Accuracy (%) | 76.2 |
| MMLU-by-task - Abstract Algebra | 33 | Accuracy (%) | 75.6 |
| MMLU-by-task - Machine Learning | 37.5 | Accuracy (%) | 71.9 |
| BoolQ | 85 | Accuracy (%) | 70.1 |
| MMLU-by-task - Formal Logic | 34.92 | Accuracy (%) | 69.2 |
| MMLU-by-task - Moral Scenarios | 30.28 | Accuracy (%) | 67.9 |
| MMLU-by-task - Elementary Mathematics | 32.01 | Accuracy (%) | 67.6 |
Interactive version: theaggregate.ai/model?slug=mpt-30b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-05.