dolly-v2-7B: benchmark results
Provider: Databricks.
Aggregate Rating 1135 ± 15, rank #10209 of 10916 rated models, from 75 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Machine Learning | 31.25 | Accuracy (%) | 43.7 |
| MMLU-by-task - Global Facts | 31 | Accuracy (%) | 36.8 |
| MMLU-by-task - ARC Challenge | 40.96 | Accuracy (%) | 35.3 |
| MMLU-by-task - HellaSwag | 52.74 | Accuracy (%) | 35.2 |
| MMLU-by-task - Human Aging | 38.57 | Accuracy (%) | 34.5 |
| MMLU-by-task - College Physics | 22.55 | Accuracy (%) | 34.3 |
| MMLU-by-task - High School Chemistry | 28.57 | Accuracy (%) | 33.2 |
| MMLU-by-task - High School World History | 29.96 | Accuracy (%) | 31.6 |
| MMLU-by-task - Conceptual Physics | 32.34 | Accuracy (%) | 31.4 |
| MMLU-by-task - Public Relations | 33.64 | Accuracy (%) | 30.2 |
| MMLU-by-task - Jurisprudence | 29.63 | Accuracy (%) | 29.6 |
| MMLU-by-task - Miscellaneous | 29.5 | Accuracy (%) | 29 |
Interactive version: theaggregate.ai/model?slug=dolly-v2-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.