Apertus-v1.1-1.5B: benchmark results

Provider: Apertus. Access: Open.

Aggregate Rating 1250 ± 35, rank #9114 of 10552 rated models, from 26 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Lara Mini Base Report (base-model protocol) - XNLI, All Languages (0-shot)43.5Accuracy (%) averaged over all languages/variants of the ben89.8
Lara Mini Base Report (base-model protocol) - XCOPA, All Languages (0-shot)59.8Accuracy (%) averaged over all languages/variants of the ben77.8
Lara Mini Base Report (base-model protocol) - Global PIQA (non-parallel), All Languages (0-shot)57.7Accuracy (%) averaged over all languages/variants of the ben75.9
Lara Mini Base Report (base-model protocol) - Global PIQA (parallel), All Languages (0-shot)25.3Accuracy (%) averaged over all languages/variants of the ben72.2
Lara Mini Base Report (base-model protocol) - T-HellaSwag, All Languages (0-shot)40.6Accuracy normalized by answer length (%) averaged over all l72.2
Lara Mini Base Report (base-model protocol) - XNLI (English) (0-shot)53.5Accuracy (%), English benchmark53.7
Lara Mini Base Report (base-model protocol) - PAWS-X, All Languages (0-shot)54.2Accuracy (%) averaged over all languages/variants of the ben42.6
Lara Mini Base Report (base-model protocol) - INCLUDE, All Languages (5-shot)37.2Accuracy (%) averaged over all languages/variants of the ben38.9
Lara Mini Base Report (base-model protocol) - PAWS (English) (0-shot)62.2Accuracy (%), English benchmark38.9
Lara Mini Base Report (base-model protocol) - COPA (0-shot)81Accuracy (%), English benchmark38
Lara Mini Base Report (base-model protocol) - PIQA (0-shot)75.4Accuracy normalized by answer length (%), English benchmark33.3
Lara Mini Base Report (base-model protocol) - HellaSwag (10-shot)65.3Accuracy normalized by answer length (%), English benchmark31.5

Interactive version: theaggregate.ai/model?slug=apertus-v1-1-1-5b · How It Works · Data refreshed daily, snapshot 2026-11-16.