SeaEval - FLORES Translation - Indonesian-to-English (Zero-Shot): leaderboard
SeaEval zero-shot Indonesian-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 | 43.37 | #561 |
| 2 | Qwen 2.5 72B Instruct | 42.16 | #454 |
| 3 | Llama 3.1 70B Cpt Sea Lionv3 Instruct | 41.78 | #548 |
| 4 | Gemma 2 9B (IT) | 40.79 | #788 |
| 5 | Qwen 2 72B Instruct | 40.44 | #576 |
| 6 | Qwen 2.5 32B Instruct | 39.23 | #498 |
| 7 | gemma2-9B-cpt-sea-lionv3-instruct | 39.22 | #705 |
| 8 | Llama 3 8B Cpt Sea Lionv2 Instruct | 39.16 | #1188 |
| 9 | Qwen 2.5 14B Instruct | 39.01 | #647 |
| 10 | Llama 3 8B Cpt Sea Lionv2.1 Instruct | 38.89 | #1024 |
| 11 | Llama 3 70B Instruct | 38.3 | #634 |
| 12 | Llama 3.1 8B Instruct | 37.36 | #1035 |
| 13 | Qwen 2.5 7B Instruct | 36.47 | #862 |
| 14 | SeaLLMs-v3-7B-Chat | 35.95 | #915 |
| 15 | Gemma 2 2B (IT) | 34.83 | #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-indonesian-to-english-zero-shot · How It Works · Data refreshed daily, snapshot 2026-10-20.