SEA-HELM (Tamil) - Causal Reasoning: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 92.05 |
| 2 | Qwen 3.5 27B | 90.03 |
| 3 | Gemma 3 27B (IT) | 89.39 |
| 4 | Qwen 3.6 27B | 88.57 |
| 5 | Qwen 3.5 122B A10B | 88.34 |
| 6 | Gemma 4 26B A4B (IT) | 87.86 |
| 7 | Mistral Medium 3.5 | 86.04 |
| 8 | Qwen 3.6 35B A3B | 84.92 |
| 9 | Llama 3.3 70B Instruct | 84.48 |
| 10 | Llama 4 Scout Instruct | 84.29 |
| 11 | Gemma 3 12B (IT) | 82.42 |
| 12 | Qwen 3 VL 32B Instruct | 82.34 |
| 13 | gemma-4-E4B-it | 79.82 |
| 14 | Qwen 3.5 35B A3B | 76.66 |
| 15 | Gemma 4 12B (IT) | 74.91 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-tamil-causal-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.