CanMT - Chinese to English: 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 English; higher is better.

Metric: Translation score (1-7) on the 125 Chinese-to-English 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

#ModelSettingScoreOverall rank
1GPT-45.52#988
2Grok 4.15.43#472
3DeepSeek V3.25.41#425
4Gemini 2.5 Flash Lite5.4#972
5Qwen 2.5 72B Instruct5.37#1124
6Seed-X-PPO-7B5.37
7GPT-4o5.35#754
8Qwen 3 14BNon-reasoning5.31#1284
9DeepSeek R15.28#484
10Qwen 2.5 14B Instruct5.26#1788
11Qwen 2.5 32B Instruct5.22#1253
12Qwen 3 32BNon-reasoning5.19#983
13Llama 3.3 70B Instruct5.14#1394
14Youdao Translate5.14
15Qwen 3 8BNon-reasoning5.03#1890

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=canmt-chinese-to-english · How It Works · Data refreshed daily, snapshot 2026-11-22.