SAHM - MCQ Average: leaderboard

Arabic financial knowledge on SAHM (2026): the mean accuracy over four multiple-choice tasks, accounting exams, business exams, Islamic finance fatwa questions and financial report sentiment, built from authentic regulatory, juristic and corporate Arabic sources. Percent; higher is better.

Metric: Mean accuracy (%) over the four multiple-choice tasks (accounting exams, business exams, fatwa MCQ, financial sentiment) of SAHM, an Arabic financial and Sharia-compliance benchmark, exact match after normalizing the chosen option, greedy decoding, mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 20 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Flash (Preview)80.52#152
2Claude Opus 4.580.27#160
3Claude Sonnet 4.580.15#261
4GPT-576.86#178
5GPT-4o75.96#751
6Claude Haiku 4.575.96#583
7Qwen 2.5 72B Instruct75.1#1117
8Llama 3.1 70B Instruct73.65#1571
9GPT-4o Mini73.61#1667
10Gemma 3 27B (IT)71.94#1324
11Fanar-1-9B-Instruct61.66#1844
12ALLaM-7B-Instruct-preview61.59#2001
13Qwen 2.5 14B Instruct61.51#1775
14Gemma 3 4B (IT)60.61#4139
15Llama 3.1 8B Instruct60.6#4600

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

Interactive version: theaggregate.ai/benchmark?slug=sahm-mcq-average · How It Works · Data refreshed daily, snapshot 2026-11-21.