SEA-HELM (Indonesian) - Metaphor Understanding: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 83.33 |
| 2 | Qwen 3.6 27B | 78.63 |
| 3 | Qwen 3.5 122B A10B | 76.34 |
| 4 | Qwen 3.5 27B | 75.92 |
| 5 | Llama 3.3 70B Instruct | 75.7 |
| 6 | Gemma 4 26B A4B (IT) | 75.57 |
| 7 | Gemma 4 12B (IT) | 75.48 |
| 8 | Qwen 3 VL 32B Instruct | 74.98 |
| 9 | Llama 4 Scout Instruct | 72.42 |
| 10 | Mistral Medium 3.5 | 72.06 |
| 11 | Gemma 3 12B (IT) | 69.77 |
| 12 | Gemma 3 27B (IT) | 69.26 |
| 13 | Qwen 3 VL 8B Instruct | 68.33 |
| 14 | Qwen 3.6 35B A3B | 68.13 |
| 15 | gemma-4-E4B-it | 67.74 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-indonesian-metaphor-understanding · How It Works · Data refreshed daily, snapshot 2026-09-19.