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

Metric: Translation score (1-7) on the 111 English-to-Chinese 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-45.33#970
2DeepSeek V3.25.31#419
3Qwen 2.5 72B Instruct5.24#1117
4DeepSeek R15.24#482
5Grok 4.15.22#462
6GPT-4o5.21#751
7Seed-X-PPO-7B5.14
8Qwen 3 32BNon-reasoning5.12#972
9Gemini 2.5 Flash Lite5.11#964
10Qwen 3 14BNon-reasoning5.07#1269
11Qwen 2.5 32B Instruct5.06#1247
12Llama 3.3 70B Instruct5#1385
13Qwen 2.5 14B Instruct5#1775
14Qwen 3 8BNon-reasoning4.91#1873
15Youdao Translate4.89

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

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