xglm-564M: benchmark results
Meta FAIR's XGLM 564M, a dense multilingual decoder-only base model trained on 500 billion sub-tokens across 30 languages; this is not an instruction-tuned release. Provider: Other. Access: Open.
Aggregate Rating 1119 ± 16, rank #10521 of 10916 rated models, from 73 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Statistics | 45.37 | Accuracy (%) | 75.3 |
| MMLU-by-task - Machine Learning | 33.04 | Accuracy (%) | 53.4 |
| MMLU-by-task - Professional Medicine | 44.49 | Accuracy (%) | 42.8 |
| MMLU-by-task - Econometrics | 27.19 | Accuracy (%) | 39.6 |
| MMLU-by-task - High School Chemistry | 29.56 | Accuracy (%) | 38.5 |
| MMLU-by-task - High School Computer Science | 34 | Accuracy (%) | 36.1 |
| MMLU-by-task - College Physics | 22.55 | Accuracy (%) | 34.3 |
| MMLU-by-task - High School US History | 28.92 | Accuracy (%) | 32 |
| MMLU-by-task - Professional Accounting | 27.66 | Accuracy (%) | 30.6 |
| MMLU-by-task - Elementary Mathematics | 26.19 | Accuracy (%) | 30 |
| MMLU-by-task - TruthfulQA MC2 | 40.43 | Accuracy (%) | 29 |
| MMLU-by-task - Conceptual Physics | 31.49 | Accuracy (%) | 28.3 |
Interactive version: theaggregate.ai/model?slug=xglm-564m · How It Works · Data refreshed daily, snapshot 2026-11-08.