Qwen-SEA-LION-v4.5-27B-IT: benchmark results
Provider: Alibaba. Access: Open.
Aggregate Rating 1651 ± 30, rank #620 of 10916 rated models, from 130 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (Filipino) - Natural Language Inference | 69.98 | Normalized Score | 100 |
| SEA-HELM (Thai) - Safety | 61.59 | Normalized Score | 100 |
| SEA-HELM (Thai) - Toxicity Detection | 50.67 | Normalized Score | 100 |
| SEA-HELM (Tamil) - Causal Reasoning | 95.75 | Normalized Score | 98.2 |
| SEA-HELM (English) - AA-LCR | 69.65 | Normalized Score | 96.5 |
| SEA-HELM (English) - MuSR | 80.56 | Normalized Score | 96.5 |
| SEA-HELM (Filipino) - NLR | 80.91 | Normalized Score | 96.5 |
| SEA-HELM (Filipino) - SEA-Safeguard | 78.3 | Normalized Score | 96.5 |
| SEA-HELM (Malay) - SEA-NLI | 67.57 | Normalized Score | 96.5 |
| SEA-HELM (Tamil) - NLR | 74.83 | Normalized Score | 96.5 |
| SEA-HELM (Vietnamese) - Causal Reasoning | 94.76 | Normalized Score | 96.5 |
| SEA-HELM (Vietnamese) - NLR | 77.49 | Normalized Score | 96.5 |
Interactive version: theaggregate.ai/model?slug=qwen-sea-lion-v4-5-27b-it · How It Works · Data refreshed daily, snapshot 2026-11-08.