bloom-560m: benchmark results
BigScience's BLOOM 560M, a transformer-based multilingual language model released under the RAIL License v1.0 by the open BigScience collaboration. Provider: BigScience. Released 2022-07-21. Access: Open.
Aggregate Rating 1112 ± 16, rank #10596 of 10916 rated models, from 80 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Statistics | 47.22 | Accuracy (%) | 83.3 |
| MMLU-by-task - Machine Learning | 37.5 | Accuracy (%) | 71.9 |
| MMLU-by-task - Econometrics | 28.95 | Accuracy (%) | 55.2 |
| Open LLM Leaderboard - MuSR | 40.31 | Score | 44.6 |
| MMLU-by-task - TruthfulQA MC2 | 42.44 | Accuracy (%) | 39.5 |
| MMLU-by-task - Professional Medicine | 42.28 | Accuracy (%) | 36.6 |
| MMLU-by-task - College Computer Science | 33 | Accuracy (%) | 36.5 |
| MMLU-by-task - TruthfulQA MC1 | 24.6 | Accuracy (%) | 28.9 |
| MMLU-by-task - High School Computer Science | 30 | Accuracy (%) | 27.4 |
| MMLU-by-task - Electrical Engineering | 27.59 | Accuracy (%) | 26 |
| MMLU-by-task - College Physics | 21.57 | Accuracy (%) | 25.7 |
| MMLU-by-task - Medical Genetics | 30 | Accuracy (%) | 25.6 |
Interactive version: theaggregate.ai/model?slug=bloom-560m · How It Works · Data refreshed daily, snapshot 2026-11-08.