Loading data...
Apertus-v1.1-0.5B: benchmark results
Provider: Apertus. Access: Open.
Aggregate Rating 1186 ± 34, rank #9497 of 10552 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
| Lara Mini Base Report (base-model protocol) - XNLI (English) (0-shot) | 54.1 | Accuracy (%), English benchmark | 65.7 |
| Lara Mini Base Report (base-model protocol) - XNLI, All Languages (0-shot) | 40.5 | Accuracy (%) averaged over all languages/variants of the ben | 64.8 |
| Lara Mini Base Report (base-model protocol) - Global PIQA (non-parallel), All Languages (0-shot) | 54.5 | Accuracy (%) averaged over all languages/variants of the ben | 39.8 |
| Lara Mini Base Report (base-model protocol) - XCOPA, All Languages (0-shot) | 55.6 | Accuracy (%) averaged over all languages/variants of the ben | 36.1 |
| Lara Mini Base Report (base-model protocol) - T-HellaSwag, All Languages (0-shot) | 34.1 | Accuracy normalized by answer length (%) averaged over all l | 16.7 |
| Lara Mini Base Report (base-model protocol) - PIQA (0-shot) | 70.4 | Accuracy normalized by answer length (%), English benchmark | 7.4 |
| Lara Mini Base Report (base-model protocol) - COPA (0-shot) | 74.8 | Accuracy (%), English benchmark | 6.5 |
| Lara Mini Base Report (base-model protocol) - Global PIQA (parallel), All Languages (0-shot) | 22.6 | Accuracy (%) averaged over all languages/variants of the ben | 6.5 |
| Lara Mini Base Report (base-model protocol) - Belebele (English) (0-shot) | 25.6 | Accuracy (%), English benchmark | 5.6 |
| Lara Mini Base Report (base-model protocol) - CRUXEval-I (2-shot) | 18 | pass@1, direct prediction, official answer parser (%) | 5.6 |
| Lara Mini Base Report (base-model protocol) - HellaSwag (10-shot) | 52.3 | Accuracy normalized by answer length (%), English benchmark | 3.7 |
| Lara Mini Base Report (base-model protocol) - MATH (4-shot) | 3 | Math-Verify equivalence, Minerva prompts, 5,000 problems ove | 3.7 |
Interactive version: theaggregate.ai/model?slug=apertus-v1-1-0-5b · How It Works · Data refreshed daily, snapshot 2026-11-16.