SAHM - Accounting Exams: leaderboard
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 January 2027. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 78.44 |
| 2 | Claude Opus 4.5 | 77.84 |
| 3 | Gemini 3 Flash (Preview) | 76.05 |
| 4 | Claude Haiku 4.5 | 67.66 |
| 5 | Qwen 2.5 72B Instruct | 65.87 |
| 6 | GPT-5 | 65.27 |
| 7 | GPT-4o | 60.48 |
| 8 | GPT-4o Mini | 58.08 |
| 9 | Gemma 3 27B (IT) | 53.89 |
| 10 | Llama 3.1 70B Instruct | 52.1 |
| 11 | SILMA-9B-Instruct-v1.0 | 50.9 |
| 12 | Gemma 2 9B (IT) | 49.1 |
| 13 | Qwen 2.5 14B Instruct | 49.1 |
| 14 | Qwen 2.5 7B Instruct | 48.5 |
| 15 | Fanar-1-9B-Instruct | 47.31 |
Interactive version: theaggregate.ai/benchmark?slug=sahm-accounting-exams · How It Works · Data refreshed daily, snapshot 2026-10-07.