Qwen-SEA-LION-v4-8B-VL: benchmark results
Provider: Alibaba. Access: Open.
Aggregate Rating 1573 ± 26, rank #1359 of 10916 rated models, from 138 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (Tamil) - Question Answering | 69.66 | Normalized Score | 96.5 |
| SEA-HELM (Indonesian) - Toxicity Detection | 54.5 | Normalized Score | 93 |
| SEA-HELM (Malay) - Toxicity Detection | 16.14 | Normalized Score | 93 |
| SEA-HELM (Thai) - Question Answering | 87.08 | Normalized Score | 93 |
| SEA-HELM (Vietnamese) - Question Answering | 81.32 | Normalized Score | 91.2 |
| SEA-HELM (Thai) - Toxicity Detection | 44.11 | Normalized Score | 82.5 |
| SEA-HELM (Vietnamese) - NLU | 70.38 | Normalized Score | 80.7 |
| SEA-HELM (Tamil) - Summarization | 11.96 | Normalized Score | 78.9 |
| SEA-HELM (Indonesian) - SEA-IFEval | 93.61 | Normalized Score | 77.2 |
| SEA-HELM (Malay) - SEA-IFEval | 84.45 | Normalized Score | 73.7 |
| SEA-HELM (Vietnamese) - SEA-NLI | 71.11 | Normalized Score | 73.7 |
| SEA-HELM (Indonesian) - Question Answering | 81.19 | Normalized Score | 71.9 |
Interactive version: theaggregate.ai/model?slug=qwen-sea-lion-v4-8b-vl · How It Works · Data refreshed daily, snapshot 2026-11-08.