SeaEval - FLORES Translation - Vietnamese-to-English (Zero-Shot): leaderboard
SeaEval zero-shot Vietnamese-to-English translation evaluation measuring BLEU quality for translation into English.
Metric: BLEU (0-100). Source: huggingface.co. Saturation forecast: Estimated already saturated. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 70B Instruct | 37.24 | #561 |
| 2 | Llama 3.1 70B Cpt Sea Lionv3 Instruct | 36.09 | #548 |
| 3 | Qwen 2.5 72B Instruct | 35.73 | #454 |
| 4 | Qwen 2.5 32B Instruct | 33.79 | #498 |
| 5 | Gemma 2 9B (IT) | 33.68 | #788 |
| 6 | Qwen 2 72B Instruct | 33.01 | #576 |
| 7 | Llama 3 8B Cpt Sea Lionv2.1 Instruct | 32.83 | #1024 |
| 8 | Llama 3 8B Cpt Sea Lionv2 Instruct | 32.78 | #1188 |
| 9 | Llama 3 70B Instruct | 32.3 | #634 |
| 10 | Qwen 2.5 14B Instruct | 32.2 | #647 |
| 11 | gemma2-9B-cpt-sea-lionv3-instruct | 31.76 | #705 |
| 12 | SeaLLMs-v3-7B-Chat | 30.98 | #915 |
| 13 | Llama 3.1 8B Instruct | 30.31 | #1035 |
| 14 | Qwen 2.5 7B Instruct | 30.28 | #862 |
| 15 | Gemma 2 2B (IT) | 27.52 | #1341 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=seaeval-flores-translation-vietnamese-to-english-zero-shot · How It Works · Data refreshed daily, snapshot 2026-10-20.