CanMT - Chinese 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 Chinese to Japanese; higher is better.

Metric: Translation score (1-7) on the 137 Chinese-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: Estimated already saturated. 22 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-45.34#970
2Grok 4.15.17#462
3DeepSeek V3.25.15#419
4GPT-4o5.11#751
5DeepSeek R15.07#482
6Gemini 2.5 Flash Lite5.07#964
7Qwen 3 32BNon-reasoning4.86#972
8Llama 3.3 70B Instruct4.81#1385
9Qwen 2.5 72B Instruct4.74#1117
10Qwen 3 14BNon-reasoning4.73#1269
11Seed-X-PPO-7B4.45
12Qwen 3 8BNon-reasoning4.42#1873
13Qwen 2.5 32B Instruct4.35#1247
14Youdao Translate4.35
15Google Translate4.33

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=canmt-chinese-to-japanese · How It Works · Data refreshed daily, snapshot 2026-11-21.