SEA-HELM (Vietnamese) - Summarization: leaderboard
Abstractive summarization of Vietnamese news articles. Normalized 0-100 score from AI Singapore's SEA-HELM leaderboard: (score - random baseline) / (maximum - baseline), floored at 0 and averaged over eight runs; higher is better.
Metric: Normalized Score. Source: leaderboard.sea-lion.ai. Saturation forecast: Estimated already saturated. 58 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama-SEA-LION-v3-70B-IT | 19.81 | #407 |
| 2 | Llama 4 Scout Instruct | 17.55 | #547 |
| 3 | Llama 3.1 8B Instruct | 17.52 | #1017 |
| 4 | Gemma 4 26B A4B (IT) (Reasoning) | 17.18 | #293 (Gemma 4 26B A4B (IT)) |
| 5 | Llama 3.3 70B Instruct | 17.13 | #541 |
| 6 | Qwen 3.5 122B A10B (Reasoning) | 17.11 | #184 (Qwen 3.5 122B A10B) |
| 7 | Qwen 3.5 27B (Reasoning) | 16.97 | #192 (Qwen 3.5 27B) |
| 8 | MERaLiON-2-10B | 16.96 | #600 |
| 9 | Qwen 3.5 35B A3B (Reasoning) | 16.9 | #268 (Qwen 3.5 35B A3B) |
| 10 | Qwen 3 14B (Reasoning) | 16.49 | #542 (Qwen 3 14B) |
| 11 | Qwen 3.6 35B A3B (Reasoning) | 16.48 | #238 (Qwen 3.6 35B A3B) |
| 12 | Apertus-8B-Instruct-2509 | 16.45 | #1028 |
| 13 | OLMo 3.1 32B Instruct | 16.41 | #755 |
| 14 | Llama-SEA-LION-v3-8B-IT | 16.3 | #800 |
| 15 | Qwen 3.6 27B (Reasoning) | 16.1 | #182 (Qwen 3.6 27B) |
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-vietnamese-summarization · How It Works · Data refreshed daily, snapshot 2026-11-05.