Apertus-v1.5-70B: benchmark results
Provider: Apertus. Access: Open.
Aggregate Rating 1536 ± 28, rank #1882 of 10916 rated models, from 131 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (Indonesian) - SEA-Safeguard | 72.77 | Normalized Score | 84.2 |
| SEA-HELM (Thai) - SEA-Safeguard | 71.18 | Normalized Score | 73.7 |
| SEA-HELM (Vietnamese) - Question Answering | 78.04 | Normalized Score | 73.7 |
| SEA-HELM (Burmese) - NLG | 48.05 | Normalized Score | 71.9 |
| SEA-HELM (Malay) - Translations | 91.32 | Normalized Score | 71.9 |
| SEA-HELM (Indonesian) - Translations | 92.87 | Normalized Score | 70.2 |
| SEA-HELM (Burmese) - Translations | 77.63 | Normalized Score | 68.4 |
| SEA-HELM (Vietnamese) - Translations | 92.15 | Normalized Score | 66.7 |
| SEA-HELM (Malay) - Safety | 40.91 | Normalized Score | 64.9 |
| SEA-HELM (Filipino) - Kalahi (LLM Judge) | 58.39 | Normalized Score | 63.2 |
| SEA-HELM (Thai) - SEA-NLI | 64.85 | Normalized Score | 63.2 |
| SEA-HELM (Vietnamese) - SEA-Safeguard | 72.46 | Normalized Score | 63.2 |
Interactive version: theaggregate.ai/model?slug=apertus-v1-5-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.