Gemma-SEA-LION-v4-4B-VL: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1494 ± 33, rank #2452 of 10916 rated models, from 131 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (Filipino) - SEA-NLI | 60.89 | Normalized Score | 87.7 |
| SEA-HELM (Vietnamese) - Sentiment Analysis | 62.76 | Normalized Score | 87.7 |
| SEA-HELM (Burmese) - Sentiment Analysis | 43.53 | Normalized Score | 82.5 |
| SEA-HELM (Tamil) - Sentiment Analysis | 95.82 | Normalized Score | 80.7 |
| SEA-HELM (Malay) - Safety | 42.15 | Normalized Score | 78.9 |
| SEA-HELM (Malay) - Toxicity Detection | 14.19 | Normalized Score | 78.9 |
| SEA-HELM (Tamil) - SEA-Safeguard | 67.48 | Normalized Score | 70.2 |
| SEA-HELM (Filipino) - Translations | 87.74 | Normalized Score | 64.9 |
| SEA-HELM (Indonesian) - SEA-NLI | 68.81 | Normalized Score | 64.9 |
| SEA-HELM (Malay) - SEA-Safeguard | 70.11 | Normalized Score | 64.9 |
| SEA-HELM (Burmese) - SEA-Safeguard | 48.51 | Normalized Score | 61.4 |
| SEA-HELM (Burmese) - Summarization | 19.16 | Normalized Score | 61.4 |
Interactive version: theaggregate.ai/model?slug=gemma-sea-lion-v4-4b-vl · How It Works · Data refreshed daily, snapshot 2026-11-08.