Apertus-SEA-LION-v4-8B-IT: benchmark results
Provider: Apertus. Access: Open.
Aggregate Rating 1451 ± 31, rank #3729 of 10916 rated models, from 130 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (Indonesian) - Summarization | 17.08 | Normalized Score | 77.2 |
| SEA-HELM (Filipino) - Toxicity Detection | 47.84 | Normalized Score | 73.7 |
| SEA-HELM (Malay) - Toxicity Detection | 13.04 | Normalized Score | 70.2 |
| SEA-HELM (Burmese) - Translations | 62.76 | Normalized Score | 56.1 |
| SEA-HELM (Indonesian) - NLG | 54.2 | Normalized Score | 56.1 |
| SEA-HELM (Indonesian) - Question Answering | 78.77 | Normalized Score | 56.1 |
| SEA-HELM (Thai) - Summarization | 22.65 | Normalized Score | 54.4 |
| SEA-HELM (Thai) - Toxicity Detection | 37.31 | Normalized Score | 52.6 |
| SEA-HELM (Burmese) - SEA-Safeguard | 20.53 | Normalized Score | 50.9 |
| SEA-HELM (Burmese) - Safety | 23.03 | Normalized Score | 49.1 |
| SEA-HELM (Thai) - NLG | 56.05 | Normalized Score | 47.4 |
| SEA-HELM (Burmese) - Toxicity Detection | 25.53 | Normalized Score | 45.6 |
Interactive version: theaggregate.ai/model?slug=apertus-sea-lion-v4-8b-it · How It Works · Data refreshed daily, snapshot 2026-11-08.