Qwen-SEA-LION-v5-9B: benchmark results
AI Singapore's SEA-LION v5 9B multimodal model (Nov 18, 2026, MIT), post-trained on Qwen3.5-9B. Provider: AI Singapore. Released 2026-11-18. Access: Open.
Aggregate Rating 1627 ± 35, rank #708 of 10524 rated models, from 132 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (Filipino) - SEA-Safeguard | 77.85 | Normalized Score | 91.9 |
| SEA-HELM (Thai) - Safety | 59.77 | Normalized Score | 91.9 |
| SEA-HELM (Tamil) - SEA-Safeguard | 82.27 | Normalized Score | 90.5 |
| SEA-HELM (Thai) - Toxicity Detection | 46.07 | Normalized Score | 90.5 |
| SEA-HELM (Vietnamese) - Question Answering | 80.35 | Normalized Score | 83.8 |
| SEA-HELM (Thai) - NLU | 63.42 | Normalized Score | 79.7 |
| SEA-HELM (Thai) - SEA-Safeguard | 73.47 | Normalized Score | 79.7 |
| SEA-HELM (Thai) - Sentiment Analysis | 40.36 | Normalized Score | 79.7 |
| SEA-HELM (Thai) - Question Answering | 86.48 | Normalized Score | 78.4 |
| SEA-HELM (English) - MathArena | 40.32 | Normalized Score | 78.3 |
| SEA-HELM (English) - AA-LCR | 66.71 | Normalized Score | 76.7 |
| SEA-HELM (Burmese) - Sentiment Analysis | 43.81 | Normalized Score | 75.7 |
Interactive version: theaggregate.ai/model?slug=qwen-sea-lion-v5-9b · How It Works · Data refreshed daily, snapshot 2026-11-22.