bloom-1b7: benchmark results
BigScience's BLOOM 1.7B, a multilingual transformer language model in the open BLOOM project, released under the RAIL License v1.0. Provider: BigScience. Released 2022-05-19. Access: Open.
Aggregate Rating 1143 ± 12, rank #1607 of 1635 rated models, from 85 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Statistics | 47.22 | Accuracy (%) | 83.3 |
| MMLU-by-task - Formal Logic | 35.71 | Accuracy (%) | 72.7 |
| MMLU-by-task - High School Physics | 33.11 | Accuracy (%) | 70.8 |
| MMLU-by-task - Moral Scenarios | 27.26 | Accuracy (%) | 59.8 |
| MMLU-by-task - College Physics | 26.47 | Accuracy (%) | 57.9 |
| MMLU-by-task - Professional Medicine | 44.85 | Accuracy (%) | 45.7 |
| MMLU-by-task - College Mathematics | 31 | Accuracy (%) | 45.5 |
| MMLU-by-task - Security Studies | 40 | Accuracy (%) | 39.1 |
| MMLU-by-task - High School Macroeconomics | 35.9 | Accuracy (%) | 37.3 |
| MMLU-by-task - Management | 38.83 | Accuracy (%) | 37 |
| MMLU-by-task - Global Facts | 31 | Accuracy (%) | 36.8 |
| MMLU-by-task - College Computer Science | 33 | Accuracy (%) | 36.5 |
Interactive version: theaggregate.ai/model?slug=bloom-1b7 · How It Works · Data refreshed daily, snapshot 2026-11-05.