Loading data...
Apertus-v1.5-8B-base: benchmark results
Provider: Apertus. Access: Open.
Aggregate Rating 1438 ± 33, rank #4427 of 10552 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
| Lara Mini Base Report (base-model protocol) - Global PIQA (parallel), All Languages (0-shot) | 30.1 | Accuracy (%) averaged over all languages/variants of the ben | 100 |
| Lara Mini Base Report (base-model protocol) - Global PIQA (non-parallel), All Languages (0-shot) | 64.3 | Accuracy (%) averaged over all languages/variants of the ben | 98.1 |
| Lara Mini Base Report (base-model protocol) - T-HellaSwag, All Languages (0-shot) | 52.7 | Accuracy normalized by answer length (%) averaged over all l | 98.1 |
| Lara Mini Base Report (base-model protocol) - XCOPA, All Languages (0-shot) | 65.2 | Accuracy (%) averaged over all languages/variants of the ben | 98.1 |
| Lara Mini Base Report (base-model protocol) - XNLI, All Languages (0-shot) | 44.6 | Accuracy (%) averaged over all languages/variants of the ben | 94.4 |
| Lara Mini Base Report (base-model protocol) - ARC-Challenge (25-shot) | 64.5 | Accuracy normalized by answer length (%), English benchmark | 92.6 |
| Lara Mini Base Report (base-model protocol) - INCLUDE, All Languages (5-shot) | 59.3 | Accuracy (%) averaged over all languages/variants of the ben | 92.6 |
| Lara Mini Base Report (base-model protocol) - Global MMLU, All Languages (5-shot) | 56.3 | Accuracy (%) averaged over all languages/variants of the ben | 90.7 |
| Lara Mini Base Report (base-model protocol) - MGSM (8 (CoT)-shot) | 54.6 | Exact match on each language's native CoT answer phrase, ave | 90.7 |
| Lara Mini Base Report (base-model protocol) - COPA (0-shot) | 87.8 | Accuracy (%), English benchmark | 89.8 |
| Lara Mini Base Report (base-model protocol) - HellaSwag (10-shot) | 80.3 | Accuracy normalized by answer length (%), English benchmark | 89.8 |
| Lara Mini Base Report (base-model protocol) - PIQA (0-shot) | 80.1 | Accuracy normalized by answer length (%), English benchmark | 88.9 |
Interactive version: theaggregate.ai/model?slug=apertus-v1-5-8b-base · How It Works · Data refreshed daily, snapshot 2026-11-16.