Gemma-SEA-LION-v4.5-E2B-IT: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1560 ± 30, rank #1545 of 10916 rated models, from 130 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (Tamil) - Question Answering | 69.02 | Normalized Score | 87.7 |
| SEA-HELM (Filipino) - Summarization | 21.83 | Normalized Score | 82.5 |
| SEA-HELM (Tamil) - Pragmatics | 60.35 | Normalized Score | 75.4 |
| SEA-HELM (Burmese) - SEA-Safeguard | 63.05 | Normalized Score | 71.9 |
| SEA-HELM (Filipino) - NLG | 54.69 | Normalized Score | 71.9 |
| SEA-HELM (Indonesian) - Pragmatics | 67.89 | Normalized Score | 70.2 |
| SEA-HELM (Tamil) - NLU | 81.42 | Normalized Score | 68.4 |
| SEA-HELM (Tamil) - Translations | 86.11 | Normalized Score | 68.4 |
| SEA-HELM (Thai) - Toxicity Detection | 41.4 | Normalized Score | 68.4 |
| SEA-HELM (Burmese) - Global MMLU Lite | 47.33 | Normalized Score | 66.7 |
| SEA-HELM (Burmese) - NLR | 48.04 | Normalized Score | 66.7 |
| SEA-HELM (Burmese) - SEA-IFEval | 66.81 | Normalized Score | 66.7 |
Interactive version: theaggregate.ai/model?slug=gemma-sea-lion-v4-5-e2b-it · How It Works · Data refreshed daily, snapshot 2026-11-08.