Qwen-SEA-LION-v4-4B-VL: benchmark results
Provider: Alibaba. Access: Open.
Aggregate Rating 1522 ± 27, rank #2044 of 10916 rated models, from 138 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (Malay) - Toxicity Detection | 15.26 | Normalized Score | 89.5 |
| SEA-HELM (Malay) - SEA-NLI | 61.93 | Normalized Score | 80.7 |
| SEA-HELM (Vietnamese) - Sentiment Analysis | 61.67 | Normalized Score | 78.9 |
| SEA-HELM (Vietnamese) - NLU | 68.81 | Normalized Score | 75.4 |
| SEA-HELM (Indonesian) - SEA-IFEval | 90.09 | Normalized Score | 66.7 |
| SEA-HELM (Vietnamese) - SEA-NLI | 67.62 | Normalized Score | 66.7 |
| SEA-HELM (Thai) - SEA-IFEval | 82.22 | Normalized Score | 64.9 |
| SEA-HELM (Thai) - Safety | 53.44 | Normalized Score | 64.9 |
| SEA-HELM (Thai) - Toxicity Detection | 40.27 | Normalized Score | 64.9 |
| SEA-HELM (Tamil) - SEA-Safeguard | 61.08 | Normalized Score | 61.4 |
| SEA-HELM (Vietnamese) - SEA-IFEval | 87.15 | Normalized Score | 61.4 |
| SEA-HELM (Indonesian) - SEA-NLI | 67.77 | Normalized Score | 59.6 |
Interactive version: theaggregate.ai/model?slug=qwen-sea-lion-v4-4b-vl · How It Works · Data refreshed daily, snapshot 2026-11-08.