Translation Set1 to en spBleu — leaderboard
Metric: Set1âen spBLEU (self-reported). Source: benchmarklist.com. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Pro | 45.6 |
| 2 | GPT-4o | 43.9 |
| 3 | Llama 3.2 90B | 43.7 |
| 4 | Claude 3.5 Sonnet | 43.5 |
| 5 | Gemini 1.5 Flash | 42.9 |
| 6 | Nova Micro | 42.6 |
| 7 | GPT-4o Mini | 41.9 |
| 8 | Gemini 1.5 Flash-8B | 41.4 |
| 9 | Claude 3.5 Haiku | 40.2 |
| 10 | Llama 3.1 8B | 36.5 |
Interactive version: theaggregate.ai/benchmark?slug=translation-set1-to-en-spbleu · How the rankings work · Data refreshed daily, snapshot 2026-07-22.