ArabCulture-Dialogue - MSA to Dialect Translation: leaderboard

ArabCulture-Dialogue (MBZUAI, 2026) asks models to translate culturally grounded dialogues from Modern Standard Arabic into the dialect of a named Arab country, zero-shot with the target country and region named in the prompt. A GPT-5 judge rates the overall quality of each translation from 1 to 5; higher is better.

Metric: Overall translation quality (1-5), GPT-5 judge (low reasoning) holistic rating, zero-shot MSA to Dialect translation of the dialogues of ArabCulture-Dialogue (13 Arab countries, parallel Modern Standard Arabic and country-dialect versions of 3,471 culturally grounded multi-turn dialogues built from ArabCulture), with the target country and region named in the prompt; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-54.53#178
2Gemini 2.5 Pro4.19#276
3ALLaM-7B-Instruct-preview3.41#2001
4c4ai-command-r7B-arabic-02-20253#2135
5Fanar-1-9B2.94#1913
6jais-adapted-7B-chat2.44#5831
7Qwen 3 8B2.35#1873
8Hala-9B1.76#1162
9Gemma 2 9B (IT)1.5#2369
10Llama 3.1 8B Instruct1.34#4600
11SILMA-9B-Instruct-v1.01.3#3847

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

Interactive version: theaggregate.ai/benchmark?slug=arabculture-dialogue-msa-to-dialect-translation · How It Works · Data refreshed daily, snapshot 2026-11-21.