SAHM - Islamic Standards QA: leaderboard
Open-ended Arabic financial reasoning on SAHM (2026): the 811 AAOIFI Sharia standards questions, each answer scored from 0 to 10 by a Gemini 2.5 Flash judge against an expert-verified reference with an additive rubric. Higher is better.
Metric: Judge score (0-10) on the 811 AAOIFI Sharia standards questions of SAHM, an Arabic financial and Sharia-compliance benchmark, each answer graded against the gold answer by a Gemini 2.5 Flash judge with an additive rubric, 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 | Gemini 3 Flash (Preview) | 9.16 | #156 |
| 2 | GPT-5 | 8.8 | #185 |
| 3 | Claude Sonnet 4.5 | 8.26 | #267 |
| 4 | Claude Opus 4.5 | 8.04 | #165 |
| 5 | Claude Haiku 4.5 | 7 | #587 |
| 6 | GPT-4o | 6.66 | #754 |
| 7 | Gemma 3 27B (IT) | 6.17 | #1341 |
| 8 | Qwen 2.5 72B Instruct | 5.63 | #1124 |
| 9 | GPT-4o Mini | 5.61 | #1680 |
| 10 | Fanar-1-9B-Instruct | 4.96 | #1829 |
| 11 | ALLaM-7B-Instruct-preview | 4.94 | #1992 |
| 12 | Qwen 2.5 14B Instruct | 4.88 | #1788 |
| 13 | Jais-2-8B-Chat | 4.25 | #2495 |
| 14 | Gemma 2 9B (IT) | 4.23 | #2383 |
| 15 | Llama 3.1 70B Instruct | 3.72 | #1579 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=sahm-islamic-standards-qa · How It Works · Data refreshed daily, snapshot 2026-11-22.