bloom-3B: benchmark results
BigScience's BLOOM 3B, a transformer-based multilingual language model released under the RAIL License v1.0 by the open BigScience collaboration. Provider: BigScience. Released 2022-05-19. Access: Open.
Aggregate Rating 1132 ± 15, rank #10280 of 10916 rated models, from 80 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Statistics | 46.76 | Accuracy (%) | 80.4 |
| MMLU-by-task - College Chemistry | 38 | Accuracy (%) | 66.4 |
| MMLU-by-task - High School Physics | 32.45 | Accuracy (%) | 66 |
| MMLU-by-task - High School Mathematics | 27.41 | Accuracy (%) | 54.7 |
| MMLU-by-task - College Mathematics | 31 | Accuracy (%) | 45.5 |
| Open LLM Leaderboard - MuSR | 39.81 | Score | 40.6 |
| MMLU-by-task - College Computer Science | 34 | Accuracy (%) | 39.6 |
| MMLU-by-task - High School Macroeconomics | 36.41 | Accuracy (%) | 39.5 |
| MMLU-by-task - Moral Scenarios | 24.69 | Accuracy (%) | 38.9 |
| MMLU-by-task - College Medicine | 32.95 | Accuracy (%) | 38.2 |
| MMLU-by-task - College Physics | 22.55 | Accuracy (%) | 34.3 |
| MMLU-by-task - Security Studies | 36.33 | Accuracy (%) | 34 |
Interactive version: theaggregate.ai/model?slug=bloom-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.