Apertus-v1.5-8B: benchmark results
Provider: Apertus. Access: Open.
Aggregate Rating 1537 ± 27, rank #1867 of 10916 rated models, from 131 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (English) - IFEval | 88.24 | Normalized Score | 73.7 |
| SEA-HELM (Vietnamese) - Question Answering | 77.63 | Normalized Score | 70.2 |
| SEA-HELM (Burmese) - Toxicity Detection | 29.31 | Normalized Score | 63.2 |
| SEA-HELM (Indonesian) - SEA-Safeguard | 70.68 | Normalized Score | 63.2 |
| SEA-HELM (Thai) - Safety | 53.26 | Normalized Score | 63.2 |
| SEA-HELM (Thai) - Toxicity Detection | 38.85 | Normalized Score | 59.6 |
| SEA-HELM (Burmese) - Natural Language Inference | 36.58 | Normalized Score | 57.9 |
| SEA-HELM (Burmese) - NLR | 37.22 | Normalized Score | 54.4 |
| SEA-HELM (Burmese) - SEA-NLI | 37.51 | Normalized Score | 54.4 |
| SEA-HELM (Burmese) - Safety | 25.79 | Normalized Score | 54.4 |
| SEA-HELM (Vietnamese) - SEA-Safeguard | 70.46 | Normalized Score | 54.4 |
| SEA-HELM (Burmese) - SEA-Safeguard | 22.28 | Normalized Score | 52.6 |
Interactive version: theaggregate.ai/model?slug=apertus-v1-5-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.