CanMT - Russian to Chinese: leaderboard

Metric: Translation score (1-7) on the 125 Russian-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: Around January 2027. 22 models tracked.

Top models

#ModelScore
1Grok 4.15
2DeepSeek V3.24.86
3Qwen 2.5 72B Instruct4.85
4Gemini 2.5 Flash Lite4.84
5Qwen 3 32B (Non-reasoning)4.83
6Qwen 3 14B (Non-reasoning)4.83
7GPT-44.79
8GPT-4o4.75
9DeepSeek R14.7
10Qwen 2.5 32B Instruct4.69
11Llama 3.3 70B Instruct4.61
12Qwen 3 8B (Non-reasoning)4.61
13Qwen 2.5 14B Instruct4.59
14Qwen 2.5 7B Instruct4.31
15Qwen 3 4B (Non-reasoning)4.24

Interactive version: theaggregate.ai/benchmark?slug=canmt-russian-to-chinese · How It Works · Data refreshed daily, snapshot 2026-10-07.