SEA-HELM (Indonesian) - Syntax (LLM Judge): leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 76.66 |
| 2 | Gemma 4 26B A4B (IT) | 69 |
| 3 | Gemma 4 12B (IT) | 65.04 |
| 4 | Qwen 3.5 27B | 65 |
| 5 | Qwen 3.5 122B A10B | 64.71 |
| 6 | Gemma 3 27B (IT) | 63.02 |
| 7 | Mistral Medium 3.5 | 61.72 |
| 8 | Llama 3.3 70B Instruct | 59.2 |
| 9 | Qwen 3 VL 32B Instruct | 58.64 |
| 10 | Qwen 3.6 27B | 57.8 |
| 11 | Mistral Small 4 | 56.64 |
| 12 | gemma-4-E4B-it | 55.13 |
| 13 | Qwen 3.6 35B A3B | 55.1 |
| 14 | Qwen 3.5 35B A3B | 53.88 |
| 15 | Llama 4 Scout Instruct | 53.11 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-indonesian-syntax-llm-judge · How It Works · Data refreshed daily, snapshot 2026-09-19.