SEA-HELM (Thai) - SEA-MT-Bench (LLM Judge): leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 27B | 83.98 |
| 2 | Qwen 3.5 122B A10B | 83.82 |
| 3 | Qwen 3.6 27B | 83.3 |
| 4 | Qwen 3.6 35B A3B | 82.56 |
| 5 | Gemma 4 31B (IT) | 82.24 |
| 6 | Gemma 4 26B A4B (IT) | 81.89 |
| 7 | Qwen 3.5 35B A3B | 81.63 |
| 8 | Qwen 3 VL 32B Instruct | 81.43 |
| 9 | Gemma 4 12B (IT) | 80.56 |
| 10 | Qwen 3 VL 8B Instruct | 78.28 |
| 11 | Qwen 3.5 9B | 77.06 |
| 12 | Mistral Medium 3.5 | 76.25 |
| 13 | gemma-4-E4B-it | 75.92 |
| 14 | Gemma 3 27B (IT) | 75.45 |
| 15 | Gemma 3 12B (IT) | 73.82 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-thai-sea-mt-bench-llm-judge · How It Works · Data refreshed daily, snapshot 2026-09-19.