Benchmark Almanac

SAHM

Gemini 3 Flash 80.5% leads since April 2026
Not in model cards

Models answer Arabic questions on financial standards, Islamic finance, and accounting. The authors report multiple-choice accuracy and grade open-ended answers separately.

Released
April 2026
Kind
Finance
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Arabic
In and out
Text → Text
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
20
Entries on its own leaderboard, 12 models we track

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:

  1. 1 Gemini 3 Flash 80.5%
  2. 2 Claude Opus 4.5 80.3%
  3. 3 Claude Sonnet 4.5 80.2%
  4. 4 GPT-5 76.9%
  5. 5 GPT-4o Mar 2025 76%
  6. 6 Claude Haiku 4.5 76%
  7. 7 ALLAM-7B Fine-tuned 75.3%
  8. 8 Qwen2.5-72B 75.1%
  9. 9 Llama 3.1-70B 73.7%
  10. 10 GPT-4o mini 73.6%
  11. 11 Gemma 3 27B 71.9%
  12. 12 Fanar-1-9B 61.7%
  13. 13 Qwen2.5-14B-Instruct 61.5%
  14. 14 Gemma 3 4B 60.6%
  15. 15 Llama 3.1-8B 60.6%
  16. 16 Gemma-2-9B-IT 58.5%
  17. 17 SILMA-9B Fine-tuned 58.4%
  18. 18 Qwen2.5-7B-Instruct 58.3%
  19. 19 Jais-2-8B Fine-tuned 57.8%
  20. 20 Mixtral-8x7B-Instruct 56.4%

Source: Official SAHM leaderboard

#EntryScoreSettingDateSource
1 Gemini 3 Flash 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 Qwen2.5-72B 75.1% Sep 2024 Official leaderboard
9 Llama 3.1-70B 73.7% Jul 2024 Official leaderboard
10 GPT-4o mini 73.6% Jul 2024 Official leaderboard
11 Gemma 3 27B 71.9% Mar 2025 Official leaderboard
12 Fanar-1-9B 61.7% Official leaderboard
13 Qwen2.5-14B-Instruct 61.5% Official leaderboard
14 Gemma 3 4B 60.6% Mar 2025 Official leaderboard
15 Llama 3.1-8B 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
#ModelScoreSettingDateSource
1 Gemini 3 Flash 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 Qwen2.5-72B 75.1% Sep 2024 Official leaderboard
8 Llama 3.1-70B 73.7% Jul 2024 Official leaderboard
9 GPT-4o mini 73.6% Jul 2024 Official leaderboard
10 Gemma 3 27B 71.9% Mar 2025 Official leaderboard
11 Gemma 3 4B 60.6% Mar 2025 Official leaderboard
12 Llama 3.1-8B 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. 1 Claude Sonnet 4.5 ↑2 78.4%
  2. 2 Claude Opus 4.5 77.8%
  3. 3 Gemini 3 Flash ↓2 76%
  4. 4 Claude Haiku 4.5 ↑2 67.7%
  5. 5 Qwen2.5-72B ↑2 65.9%
  6. 6 GPT-5 ↓2 65.3%
  7. 7 GPT-4o Mar 2025 ↓2 60.5%
  8. 8 GPT-4o mini ↑1 58.1%
  9. 9 Gemma 3 27B ↑1 53.9%
  10. 10 Llama 3.1-70B ↓2 52.1%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind
Own leaderboard Not tested since Apr 2026

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.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Gemini 3 Flash GPT-5 GPT-4o Qwen2.5-72B 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Gemini 3 Flash Qwen2.5-72B

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

All 637 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.

How we check