SEA-HELM (Filipino) - Sentiment Analysis: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 67.68 |
| 2 | Gemma 4 12B (IT) | 66.78 |
| 3 | Gemma 4 26B A4B (IT) | 63.39 |
| 4 | gemma-4-E4B-it | 61.48 |
| 5 | Qwen 3.5 122B A10B | 60.8 |
| 6 | Qwen 3 VL 32B Instruct | 59.91 |
| 7 | Qwen 3.5 27B | 59.49 |
| 8 | Qwen 3.5 35B A3B | 59.38 |
| 9 | Qwen 3.6 35B A3B | 57.46 |
| 10 | Qwen 3 VL 8B Instruct | 57.39 |
| 11 | Gemma 3 27B (IT) | 57.2 |
| 12 | Gemma 3 12B (IT) | 56.99 |
| 13 | Llama 3.3 70B Instruct | 55.74 |
| 14 | Gemma 3 4B (IT) | 55.22 |
| 15 | Gemma 4 E2B (IT) | 54.82 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-filipino-sentiment-analysis · How It Works · Data refreshed daily, snapshot 2026-09-19.