SEA-HELM (Burmese) - Sentiment Analysis: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | gemma-4-E4B-it | 49.51 |
| 2 | Gemma 3 12B (IT) | 49.5 |
| 3 | Gemma 3 27B (IT) | 46.25 |
| 4 | Qwen 3 VL 32B Instruct | 45.63 |
| 5 | Qwen 3.5 35B A3B | 45.1 |
| 6 | Qwen 3.6 35B A3B | 43.72 |
| 7 | Qwen 3.6 27B | 43.63 |
| 8 | Gemma 4 12B (IT) | 43.55 |
| 9 | Gemma 4 31B (IT) | 43.17 |
| 10 | Gemma 4 26B A4B (IT) | 43.02 |
| 11 | Qwen 3.5 122B A10B | 41.69 |
| 12 | Qwen 3.5 27B | 41.63 |
| 13 | Gemma 4 E2B (IT) | 41.13 |
| 14 | Qwen 3.5 9B | 40.08 |
| 15 | Llama 4 Scout Instruct | 40 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-burmese-sentiment-analysis · How It Works · Data refreshed daily, snapshot 2026-09-19.