SEA-HELM (Thai) - Sentiment Analysis: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 26B A4B (IT) | 42.97 |
| 2 | Gemma 4 31B (IT) | 41.49 |
| 3 | Gemma 3 27B (IT) | 38.96 |
| 4 | Qwen 3.5 122B A10B | 38.8 |
| 5 | Gemma 3 12B (IT) | 38.58 |
| 6 | Qwen 3.6 27B | 37.62 |
| 7 | Qwen 3 VL 32B Instruct | 37 |
| 8 | Gemma 4 12B (IT) | 36.18 |
| 9 | Qwen 3.6 35B A3B | 35.92 |
| 10 | Qwen 3.5 27B | 35.46 |
| 11 | Qwen 3.5 35B A3B | 35 |
| 12 | Mistral Medium 3.5 | 34.83 |
| 13 | Llama 4 Scout Instruct | 34.42 |
| 14 | Qwen 3 VL 8B Instruct | 34.26 |
| 15 | Gemma 3 4B (IT) | 34.2 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-thai-sentiment-analysis · How It Works · Data refreshed daily, snapshot 2026-09-19.