SEA-HELM (Thai) - Causal Reasoning: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 96.83 |
| 2 | Gemma 4 26B A4B (IT) | 92.26 |
| 3 | Llama 3.3 70B Instruct | 92 |
| 4 | Gemma 4 12B (IT) | 91.75 |
| 5 | Qwen 3.5 27B | 90.86 |
| 6 | Qwen 3.6 27B | 90.77 |
| 7 | Qwen 3 VL 32B Instruct | 88.9 |
| 8 | Qwen 3.5 122B A10B | 88.88 |
| 9 | Llama 4 Scout Instruct | 88.41 |
| 10 | Gemma 3 27B (IT) | 87.9 |
| 11 | Gemma 3 12B (IT) | 85.94 |
| 12 | gemma-4-E4B-it | 82.78 |
| 13 | Qwen 3 VL 8B Instruct | 81.64 |
| 14 | Qwen 3.6 35B A3B | 80.12 |
| 15 | Mistral Medium 3.5 | 78.19 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-thai-causal-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.