CanMT - English to Japanese: leaderboard
CanMT (2026) is a culture-aware machine translation benchmark of novel sentences containing culture-specific items, scored by an LLM judge with references on five translation-quality dimensions. This board is the translation score on a 1 to 7 scale for English to Japanese; higher is better.
Metric: Translation score (1-7) on the 103 English-to-Japanese CanMT sentences containing culture-specific items, GPT-5-nano judge with the reference translation scoring contextual accuracy, cultural adaptation, functional equivalence, fidelity and naturalness on 7-point Likert scales, averaged per sentence; default translation prompt; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 22 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Grok 4.1 | 5.34 | #472 | |
| 2 | DeepSeek V3.2 | 5.21 | #425 | |
| 3 | GPT-4 | 5.16 | #988 | |
| 4 | DeepSeek R1 | 5.08 | #484 | |
| 5 | Gemini 2.5 Flash Lite | 5.08 | #972 | |
| 6 | GPT-4o | 4.99 | #754 | |
| 7 | Qwen 2.5 72B Instruct | 4.84 | #1124 | |
| 8 | Llama 3.3 70B Instruct | 4.83 | #1394 | |
| 9 | Seed-X-PPO-7B | 4.69 | ||
| 10 | Qwen 3 14B | Non-reasoning | 4.65 | #1284 |
| 11 | Google Translate | 4.64 | ||
| 12 | Qwen 3 32B | Non-reasoning | 4.47 | #983 |
| 13 | Qwen 2.5 32B Instruct | 4.4 | #1253 | |
| 14 | Qwen 3 8B | Non-reasoning | 4.25 | #1890 |
| 15 | Qwen 2.5 14B Instruct | 4.08 | #1788 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=canmt-english-to-japanese · How It Works · Data refreshed daily, snapshot 2026-11-22.