bloomz-1b1: benchmark results
Provider: Other.
Aggregate Rating 1297 ± 29, rank #8788 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Greek MMLU - Other | 36.14 | Accuracy (%) | 17.3 |
| Greek MMLU | 35.07 | Accuracy (%) | 14.8 |
| Greek MMLU - Social Sciences | 34.26 | Accuracy (%) | 14.2 |
| Greek MMLU - Greek-Specific | 32.68 | Accuracy (%) | 13.6 |
| Greek MMLU - STEM | 35.64 | Accuracy (%) | 13.6 |
| Greek MMLU - Humanities | 34.37 | Accuracy (%) | 11.1 |
| UrduMMLU (Urdu Prompt) | 25.31 | Overall exact-match accuracy (%) on UrduMMLU's Urdu multiple | 7.1 |
| UrduMMLU (Urdu Prompt) - Humanities | 25.89 | Humanities (10,982 questions: ethics, fine arts, Islamic stu | 7.1 |
| UrduMMLU (Urdu Prompt) - STEM | 24.53 | STEM (5,113 questions: biology, chemistry, computer science, | 7.1 |
| UrduMMLU (Urdu Prompt) - General Knowledge | 24.52 | General knowledge (1,362 questions, the Other domain) exact- | 3.6 |
| UrduMMLU (Urdu Prompt) - Profession | 23.54 | Profession (973 questions: professional development and stud | 3.6 |
| UrduMMLU (Urdu Prompt) - Social Sciences | 25.37 | Social Sciences (7,959 questions in 11 subjects, including P | 3.6 |
Interactive version: theaggregate.ai/model?slug=bloomz-1b1 · How It Works · Data refreshed daily, snapshot 2026-11-08.