SAHM - Business Exams: leaderboard
Metric: Accuracy (%) on the 183 business 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 January 2027. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 78.14 |
| 2 | Llama 3.1 70B Instruct | 77.6 |
| 3 | GPT-4o Mini | 77.6 |
| 4 | Claude Sonnet 4.5 | 76.5 |
| 5 | Claude Opus 4.5 | 76.5 |
| 6 | Qwen 2.5 72B Instruct | 74.86 |
| 7 | Gemini 3 Flash (Preview) | 74.86 |
| 8 | Claude Haiku 4.5 | 73.77 |
| 9 | Gemma 3 27B (IT) | 73.22 |
| 10 | GPT-5 | 72.68 |
| 11 | SILMA-9B-Instruct-v1.0 | 69.4 |
| 12 | ALLaM-7B-Instruct-preview | 68.31 |
| 13 | Gemma 3 4B (IT) | 67.76 |
| 14 | Fanar-1-9B-Instruct | 66.12 |
| 15 | Gemma 2 9B (IT) | 63.39 |
Interactive version: theaggregate.ai/benchmark?slug=sahm-business-exams · How It Works · Data refreshed daily, snapshot 2026-10-07.