CanMT - Spanish 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 Spanish to English; higher is better.

Metric: Translation score (1-7) on the 134 Spanish-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-45.24#988
2Grok 4.15.22#472
3DeepSeek R15.16#484
4DeepSeek V3.25.1#425
5GPT-4o5.07#754
6Gemini 2.5 Flash Lite5.05#972
7Llama 3.3 70B Instruct5.04#1394
8Qwen 2.5 72B Instruct5.01#1124
9Qwen 2.5 32B Instruct4.99#1253
10Qwen 3 32BNon-reasoning4.92#983
11Qwen 2.5 14B Instruct4.89#1788
12Seed-X-PPO-7B4.86
13Qwen 3 14BNon-reasoning4.85#1284
14Mixtral 8x7B Instruct4.81#4692
15Qwen 2.5 7B Instruct4.61#2732

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

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