SEA-HELM (Tamil) - Linguistic Diagnostics: leaderboard
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 75.24 |
| 2 | Gemma 4 26B A4B (IT) | 72.4 |
| 3 | Qwen 3.5 27B | 71.71 |
| 4 | Qwen 3 VL 32B Instruct | 71.68 |
| 5 | Qwen 3.5 122B A10B | 71.59 |
| 6 | Gemma 3 27B (IT) | 71.18 |
| 7 | Qwen 3.6 27B | 69.51 |
| 8 | Llama 4 Scout Instruct | 67.28 |
| 9 | Qwen 3.6 35B A3B | 66.57 |
| 10 | Mistral Medium 3.5 | 63.77 |
| 11 | Gemma 4 12B (IT) | 63.72 |
| 12 | Gemma 3 12B (IT) | 59.46 |
| 13 | Llama 3.3 70B Instruct | 55.57 |
| 14 | gemma-4-E4B-it | 55.37 |
| 15 | Qwen 3 VL 8B Instruct | 52.09 |
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-tamil-linguistic-diagnostics · How It Works · Data refreshed daily, snapshot 2026-09-19.