SEA-HELM (Burmese): leaderboard
AI Singapore’s SEA-HELM restricted to Burmese: the mean over its natural-language understanding, generation, reasoning, instruction-following and cultural tasks in that language. SEA-HELM exists because Southeast Asian languages are where English-first models lose the most, and the per-language boards are where that shows.
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. Saturation forecast: Around January 2027. 58 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 26B A4B (IT) (Reasoning) | 69.37 | #297 (Gemma 4 26B A4B (IT)) |
| 2 | Qwen 3.5 122B A10B (Reasoning) | 69.16 | #173 (Qwen 3.5 122B A10B) |
| 3 | Qwen 3.6 27B (Reasoning) | 68.37 | #170 (Qwen 3.6 27B) |
| 4 | Qwen 3.5 27B (Reasoning) | 67.55 | #187 (Qwen 3.5 27B) |
| 5 | Qwen 3.5 35B A3B (Reasoning) | 66.82 | #256 (Qwen 3.5 35B A3B) |
| 6 | Qwen 3.6 35B A3B (Reasoning) | 65.61 | #226 (Qwen 3.6 35B A3B) |
| 7 | Qwen 3.5 9B (Reasoning) | 60.41 | #379 (Qwen 3.5 9B) |
| 8 | Qwen 3 32B (Thinking) | 53.9 | #443 (Qwen 3 32B) |
| 9 | Llama 4 Scout Instruct | 52.7 | #539 |
| 10 | Qwen 3.5 4B (Reasoning) | 52.41 | #475 (Qwen 3.5 4B) |
| 11 | Gemma 3 27B (IT) | 51.37 | #523 |
| 12 | Qwen 3 VL 32B Instruct | 50.47 | #283 |
| 13 | Qwen 3 14B (Reasoning) | 47.74 | #537 (Qwen 3 14B) |
| 14 | GPT-OSS-120B (Reasoning) | 46.9 | #341 (GPT-OSS-120B) |
| 15 | Gemma 3 12B (IT) | 43.45 | #664 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=sea-helm-burmese · How It Works · Data refreshed daily, snapshot 2026-10-20.