Benchmark Almanac

QIAS 2025 Islamic Knowledge Assessment

PuxAI 93.7% tops its leaderboard
Not in model cards

Models answer Arabic multiple-choice questions about classical Islamic texts. The released test contains 1,000 rows and 729 distinct questions.

HIAST reported 92.59% test accuracy with few-shot Claude Opus 4. The organizers ranked ten teams on this task.

Made by
QIAS organizers
Released
May 2025
Kind
Exam questions
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Arabic
In and out
Text → Text
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
Anyone
10
Entries on its own leaderboard, 0 models we track

PuxAI tops the leaderboard with 93.7%

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.

  1. 1 PuxAI 93.7%
  2. 2 Athar 92.7%
  3. 3 HIAST 92.6%
  4. 4 N&N 89.8%
  5. 5 Tokenizers United 87.4%
  6. 6 SEA_Team 86%
  7. 7 teams60 84.9%
  8. 8 Transformer_Tafsir 79.7%
  9. 9 CIS-RG 78.7%
  10. 10 QU-NLP 71.1%

Source: Official QIAS 2025 Islamic Knowledge Assessment leaderboard

#EntryScoreSettingSubmitted byDateSource
1 PuxAI 93.7% VNU-HCM University of Information Technology Official leaderboard
2 Athar 92.7% University of Khartoum, International Islamic University Malaysia Official leaderboard
3 HIAST 92.6% Higher Institute for Applied Sciences and Technology Official leaderboard
4 N&N 89.8% King Saud University Official leaderboard
5 Tokenizers United 87.4% Nile University Official leaderboard
6 SEA_Team 86% University of Leeds Official leaderboard
7 teams60 84.9% MBZUAI Official leaderboard
8 Transformer_Tafsir 79.7% University of Osnabrueck Official leaderboard
9 CIS-RG 78.7% Sinai University Official leaderboard
10 QU-NLP 71.1% Qatar University Official 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 10 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on sites.google.com: 10 entries at the last read, none a model we track.
  • 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