SAHM - Accounting Exams: leaderboard
Arabic financial knowledge on SAHM (2026): the 167 accounting exam questions of the benchmark, drawn from authentic Arabic regulatory, juristic and corporate sources and answered as multiple choice. Accuracy in percent; higher is better.
Metric: Accuracy (%) on the 167 accounting exam questions 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 78.44 | #261 |
| 2 | Claude Opus 4.5 | 77.84 | #160 |
| 3 | Gemini 3 Flash (Preview) | 76.05 | #152 |
| 4 | Claude Haiku 4.5 | 67.66 | #583 |
| 5 | Qwen 2.5 72B Instruct | 65.87 | #1117 |
| 6 | GPT-5 | 65.27 | #178 |
| 7 | GPT-4o | 60.48 | #751 |
| 8 | GPT-4o Mini | 58.08 | #1667 |
| 9 | Gemma 3 27B (IT) | 53.89 | #1324 |
| 10 | Llama 3.1 70B Instruct | 52.1 | #1571 |
| 11 | SILMA-9B-Instruct-v1.0 | 50.9 | #3847 |
| 12 | Gemma 2 9B (IT) | 49.1 | #2369 |
| 13 | Qwen 2.5 14B Instruct | 49.1 | #1775 |
| 14 | Qwen 2.5 7B Instruct | 48.5 | #2723 |
| 15 | Fanar-1-9B-Instruct | 47.31 | #1844 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=sahm-accounting-exams · How It Works · Data refreshed daily, snapshot 2026-11-21.