SAHM
Models answer Arabic questions on financial standards, Islamic finance, and accounting. The authors report multiple-choice accuracy and grade open-ended answers separately.
- Made by
- Rania Elbadry and colleagues
- Released
- April 2026
- Kind
- Finance
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Language
- Arabic
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Law and finance
- Strongest model tested
-
Gemini 3 Flash #60 on the capability index
- Last model added
- December 2025
- Scores refreshed
- November 20th, 2026
Gemini 3 Flash leads with 80.5% among models released by December 2025 Gemini 3 Flash leads with 80.5% among models released by December 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 80.5
Gemini 3 Flash
- 80.3 Claude Opus 4.5
- 80.2 Claude Sonnet 4.5
- 76.9 GPT-5
- 76.0 GPT-4o
- 76.0 Claude Haiku 4.5
- 75.3 ALLAM-7B
- 75.1
Qwen2.5-72B
- 73.7
Llama 3.1-70B
- 73.6 GPT-4o mini
- 71.9
Gemma 3 27B
- 61.7 Fanar-1-9B
- 61.5 Qwen2.5-14B-Instruct
- 60.6
Gemma 3 4B
- 60.6
Llama 3.1-8B
- 58.5 Gemma-2-9B-IT
- 58.4 SILMA-9B
- 58.3 Qwen2.5-7B-Instruct
- 57.8 Jais-2-8B
- 56.4 Mixtral-8x7B-Instruct
- 1
Gemini 3 Flash 80.5%
- 2 Claude Opus 4.5 80.3%
- 3 Claude Sonnet 4.5 80.2%
- 4 GPT-5 76.9%
- 5 GPT-4o Mar 2025 76%
- 6 Claude Haiku 4.5 76%
- 7 ALLAM-7B Fine-tuned 75.3%
- 8
Qwen2.5-72B 75.1%
- 9
Llama 3.1-70B 73.7%
- 10 GPT-4o mini 73.6%
- 11
Gemma 3 27B 71.9%
- 12 Fanar-1-9B 61.7%
- 13 Qwen2.5-14B-Instruct 61.5%
- 14
Gemma 3 4B 60.6%
- 15
Llama 3.1-8B 60.6%
- 16 Gemma-2-9B-IT 58.5%
- 17 SILMA-9B Fine-tuned 58.4%
- 18 Qwen2.5-7B-Instruct 58.3%
- 19 Jais-2-8B Fine-tuned 57.8%
- 20 Mixtral-8x7B-Instruct 56.4%
Source: Official SAHM leaderboard
- 1
Gemini 3 Flash 80.5%
- 2 Claude Opus 4.5 80.3%
- 3 Claude Sonnet 4.5 80.2%
- 4 GPT-5 76.9%
- 5 GPT-4o Mar 2025 76%
- 6 Claude Haiku 4.5 76%
- 7
Qwen2.5-72B 75.1%
- 8
Llama 3.1-70B 73.7%
- 9 GPT-4o mini 73.6%
- 10
Gemma 3 27B 71.9%
- 11
Gemma 3 4B 60.6%
- 12
Llama 3.1-8B 60.6%
Source: Official SAHM leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 80.5% | Dec 2025 | Official leaderboard | |
| 2 | Claude Opus 4.5 | 80.3% | Nov 2025 | Official leaderboard | |
| 3 | Claude Sonnet 4.5 | 80.2% | Sep 2025 | Official leaderboard | |
| 4 | GPT-5 | 76.9% | Aug 2025 | Official leaderboard | |
| 5 | GPT-4o Mar 2025 | 76% | Mar 2025 | Official leaderboard | |
| 6 | Claude Haiku 4.5 | 76% | Oct 2025 | Official leaderboard | |
| 7 | ALLAM-7B | 75.3% | Fine-tuned | Official leaderboard | |
| 8 | | 75.1% | Sep 2024 | Official leaderboard | |
| 9 | | 73.7% | Jul 2024 | Official leaderboard | |
| 10 | GPT-4o mini | 73.6% | Jul 2024 | Official leaderboard | |
| 11 | | 71.9% | Mar 2025 | Official leaderboard | |
| 12 | Fanar-1-9B | 61.7% | Official leaderboard | ||
| 13 | Qwen2.5-14B-Instruct | 61.5% | Official leaderboard | ||
| 14 | | 60.6% | Mar 2025 | Official leaderboard | |
| 15 | | 60.6% | Jul 2024 | Official leaderboard | |
| 16 | Gemma-2-9B-IT | 58.5% | Official leaderboard | ||
| 17 | SILMA-9B | 58.4% | Fine-tuned | Official leaderboard | |
| 18 | Qwen2.5-7B-Instruct | 58.3% | Official leaderboard | ||
| 19 | Jais-2-8B | 57.8% | Fine-tuned | Official leaderboard | |
| 20 | Mixtral-8x7B-Instruct | 56.4% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 80.5% | Dec 2025 | Official leaderboard | |
| 2 | Claude Opus 4.5 | 80.3% | Nov 2025 | Official leaderboard | |
| 3 | Claude Sonnet 4.5 | 80.2% | Sep 2025 | Official leaderboard | |
| 4 | GPT-5 | 76.9% | Aug 2025 | Official leaderboard | |
| 5 | GPT-4o Mar 2025 | 76% | Mar 2025 | Official leaderboard | |
| 6 | Claude Haiku 4.5 | 76% | Oct 2025 | Official leaderboard | |
| 7 | | 75.1% | Sep 2024 | Official leaderboard | |
| 8 | | 73.7% | Jul 2024 | Official leaderboard | |
| 9 | GPT-4o mini | 73.6% | Jul 2024 | Official leaderboard | |
| 10 | | 71.9% | Mar 2025 | Official leaderboard | |
| 11 | | 60.6% | Mar 2025 | Official leaderboard | |
| 12 | | 60.6% | Jul 2024 | Official leaderboard |
Rankings by part
We read 7 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Accounting, Business and Fatwā. Gemini 3 Flash leads 4 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Accounting
12 models we track have a score here.
- 1 Claude Sonnet 4.5 ↑2 78.4%
- 2 Claude Opus 4.5 77.8%
- 3
Gemini 3 Flash ↓2 76%
- 4 Claude Haiku 4.5 ↑2 67.7%
- 5
Qwen2.5-72B ↑2 65.9%
- 6 GPT-5 ↓2 65.3%
- 7 GPT-4o Mar 2025 ↓2 60.5%
- 8 GPT-4o mini ↑1 58.1%
- 9
Gemma 3 27B ↑1 53.9%
- 10
Llama 3.1-70B ↓2 52.1%
Business
12 models we track have a score here.
- 1 GPT-4o Mar 2025 ↑4 78.1%
- 2 GPT-4o mini ↑7 77.6%
- 3
Llama 3.1-70B ↑5 77.6%
- 4 Claude Sonnet 4.5 ↓1 76.5%
- 5 Claude Opus 4.5 ↓3 76.5%
- 6
Qwen2.5-72B ↑1 74.9%
- 7
Gemini 3 Flash ↓6 74.9%
- 8 Claude Haiku 4.5 ↓2 73.8%
- 9
Gemma 3 27B ↑1 73.2%
- 10 GPT-5 ↓6 72.7%
Fatwā
12 models we track have a score here.
- 1 Claude Opus 4.5 ↑1 91.8%
- 2 GPT-5 ↑2 90.8%
- 3
Gemini 3 Flash ↓2 89.9%
- 4 Claude Sonnet 4.5 ↓1 88.2%
- 5 GPT-4o Mar 2025 87.7%
- 6
Llama 3.1-70B ↑2 84.9%
- 7 Claude Haiku 4.5 ↓1 84.9%
- 8
Qwen2.5-72B ↓1 84.7%
- 9 GPT-4o mini 81.8%
- 10
Gemma 3 27B 80.7%
Sentiment
12 models we track have a score here.
- 1
Gemini 3 Flash 81.3%
- 2
Llama 3.1-70B ↑6 80%
- 3
Gemma 3 27B ↑7 80%
- 4 GPT-5 78.8%
- 5 GPT-4o Mar 2025 77.5%
- 6 Claude Sonnet 4.5 ↓3 77.5%
- 7 Claude Haiku 4.5 ↓1 77.5%
- 8 GPT-4o mini ↑1 75%
- 9
Qwen2.5-72B ↓2 75%
- 10
Gemma 3 4B ↑1 75%
Event-Cause QA
12 models we track have a score here.
- 1
Gemini 3 Flash 9.84
- 2 GPT-5 ↑2 9.68
- 3 Claude Opus 4.5 ↓1 9.68
- 4 Claude Sonnet 4.5 ↓1 9.34
- 5 Claude Haiku 4.5 ↑1 9.11
- 6
Gemma 3 27B ↑4 8.72
- 7 GPT-4o Mar 2025 ↓2 8.31
- 8
Qwen2.5-72B ↓1 8.10
- 9 GPT-4o mini 7.96
- 10
Gemma 3 4B ↑1 7.41
Islamic-Standards-QA
12 models we track have a score here.
- 1
Gemini 3 Flash 9.16
- 2 GPT-5 ↑2 8.80
- 3 Claude Sonnet 4.5 8.26
- 4 Claude Opus 4.5 ↓2 8.04
- 5 Claude Haiku 4.5 ↑1 7.00
- 6 GPT-4o Mar 2025 ↓1 6.66
- 7
Gemma 3 27B ↑3 6.17
- 8
Qwen2.5-72B ↓1 5.63
- 9 GPT-4o mini 5.61
- 10
Llama 3.1-70B ↓2 3.72
Fatwa-QA
12 models we track have a score here.
- 1
Gemini 3 Flash 9.16
- 2 Claude Opus 4.5 8.81
- 3 GPT-5 ↑1 8.05
- 4 Claude Sonnet 4.5 ↓1 7.60
- 5 Claude Haiku 4.5 ↑1 6.53
- 6 GPT-4o Mar 2025 ↓1 6.52
- 7
Qwen2.5-72B 5.39
- 8 GPT-4o mini ↑1 5.31
- 9
Gemma 3 27B ↑1 5.19
- 10
Llama 3.1-70B ↓2 4.76
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SAHM leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official SAHM leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 11 months ago, in December 2025, for Gemini 3 Flash. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (20 entries).
- Pass Models scored 12 models we track, plus 8 other entries on its leaderboard.
- Warning Newest score The newest came 11 months ago, in December 2025, for Gemini 3 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3 Flash (#60).
- Pass Headroom The best is 80.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on mbzuai-nlp.github.io: 12 rows for models we track and 8 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.