bloom-7b1: benchmark results
BigScience's BLOOM 7.1B, a multilingual decoder-only transformer modified from Megatron-LM GPT-2, released under the RAIL License as part of the open BLOOM project. Provider: BigScience. Released 2022-05-19. Access: Open.
Aggregate Rating 1163 ± 12, rank #1613 of 1656 rated models, from 90 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 32 | Accuracy (%) | 53.7 |
| MMLU-by-task - Global Facts | 33 | Accuracy (%) | 51.6 |
| MMLU-by-task - High School Statistics | 38.43 | Accuracy (%) | 50.1 |
| MMLU-by-task - High School Mathematics | 26.67 | Accuracy (%) | 45.9 |
| MMLU-by-task - Elementary Mathematics | 27.51 | Accuracy (%) | 43.5 |
| MMLU-by-task - High School Computer Science | 35 | Accuracy (%) | 37.2 |
| MMLU-by-task - Machine Learning | 29.46 | Accuracy (%) | 35.2 |
| MMLU-by-task - College Computer Science | 32 | Accuracy (%) | 32.6 |
| MMLU-by-task - Conceptual Physics | 32.34 | Accuracy (%) | 31.4 |
| MMLU-by-task - Human Aging | 36.32 | Accuracy (%) | 31.2 |
| MMLU-by-task - International Law | 36.36 | Accuracy (%) | 29.2 |
| MMLU-by-task - Public Relations | 32.73 | Accuracy (%) | 28.8 |
Interactive version: theaggregate.ai/model?slug=bloom-7b1 · How It Works · Data refreshed daily, snapshot 2026-10-20.