Benchmark Almanac

IslamicFaithQA

Fanar-2-27B 57.3% tops its leaderboard gpt-oss-20b 21.6% leads the models we track
Not in model cards

Models answer short Islamic knowledge questions in Arabic and English. A model judges their answers against reference answers.

The Fanar-Sadiq report scored seven systems on IslamicFaithQA. GPT-4.1 judged their answers. Fanar-Sadiq scored 65.4%.

Released
January 2026
Kind
Expert-written questions
Level
University
Scored
Graded by a model
Answers
Short answer
Tasks
All public
Measures
Capability
Language
Arabic, English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Qwen3-14B #139 on the capability index
Last model added
August 2025
Scores refreshed
November 20th, 2026
15
Entries in its paper, 7 models we track

Fanar-2-27B tops the leaderboard with 57.3% gpt-oss-20b leads with 21.6% among models released by August 2025

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. The best model we track is gpt-oss-20b, at 21.6%. This view shows only models we track, each at its best.

The newest model with a score here came out in August 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 Fanar-2-27B Agentic RAG 57.3%
  2. 2 Qwen3-4B-2507 Agentic RAG 48.9%
  3. 3 Fanar-1-9B RAG 41.2%
  4. 4 ALLaM-7B RAG 40.8%
  5. 5 AceGPT-v2-8B 25.9%
  6. 6 EuroLLM-9B 25.7%
  7. 7 SILMA-9B-v1.0 24.4%
  8. 8 gpt-oss-20b 21.6%
  9. 9 Llama 3.1-8B 19.4%
  10. 10 Mistral 7B v0.2 18.9%
  11. 11 SeaLLM-7B-v3 17.7%
  12. 12 Qwen2.5-3B 15.5%
  13. 13 Qwen3-14B 15%
  14. 14 Llama 2-7B 11.6%
  15. 15 Qwen3-8B 8.65%

Source: The IslamicFaithQA paper

#EntryScoreSettingDateSource
1 Fanar-2-27B 57.3% Agentic RAG Official leaderboard
2 Qwen3-4B-2507 48.9% Agentic RAG Official leaderboard
3 Fanar-1-9B 41.2% RAG Official leaderboard
4 ALLaM-7B 40.8% RAG Official leaderboard
5 AceGPT-v2-8B 25.9% Official leaderboard
6 EuroLLM-9B 25.7% Official leaderboard
7 SILMA-9B-v1.0 24.4% Official leaderboard
8 gpt-oss-20b 21.6% Aug 2025 Official leaderboard
9 Llama 3.1-8B 19.4% Jul 2024 Official leaderboard
10 Mistral 7B v0.2 18.9% Dec 2023 Official leaderboard
11 SeaLLM-7B-v3 17.7% Official leaderboard
12 Qwen2.5-3B 15.5% Sep 2024 Official leaderboard
13 Qwen3-14B 15% Apr 2025 Official leaderboard
14 Llama 2-7B 11.6% Jul 2023 Official leaderboard
15 Qwen3-8B 8.65% Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 gpt-oss-20b 21.6% Aug 2025 Official leaderboard
2 Llama 3.1-8B 19.4% Jul 2024 Official leaderboard
3 Mistral 7B v0.2 18.9% Dec 2023 Official leaderboard
4 Qwen2.5-3B 15.5% Sep 2024 Official leaderboard
5 Qwen3-14B 15% Apr 2025 Official leaderboard
6 Llama 2-7B 11.6% Jul 2023 Official leaderboard
7 Qwen3-8B 8.65% Apr 2025 Official leaderboard

Rankings by part

We read 2 parts from the benchmark’s paper: Arabic and English. Each ranks models on one part of the test. Qwen3-14B leads Arabic and gpt-oss-20b leads English. Arrows show how far a model moved from its overall rank among the models we track.

Arabic

7 models we track have a score here.

  1. 1 Qwen3-14B ↑4 16%
  2. 2 gpt-oss-20b ↓1 15.9%
  3. 3 Mistral 7B v0.2 13.5%
  4. 4 Llama 3.1-8B ↓2 13%
  5. 5 Qwen2.5-3B ↓1 11%
  6. 6 Qwen3-8B ↑1 8.80%
  7. 7 Llama 2-7B ↓1 4.40%

Number one over time

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

OpenAI
Benchmark paper Not tested since Jan 2026
gpt-oss-20b 21.6%

Source: The IslamicFaithQA paper

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
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 2025 Near the ceiling (85%) gpt-oss-20b Llama 3.1-8B Mistral 7B v0.2 Llama 2-7B 0% 20% 40% 60% 80% 100% 2024 2025 Near the ceiling (85%) gpt-oss-20b Mistral 7B v0.2

Source: Official IslamicFaithQA 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 15 months ago, in August 2025, for gpt-oss-20b. 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 benchmark’s paper (15 entries).
  • Pass Models scored 7 models we track, plus 8 other entries on its leaderboard.
  • Warning Newest score The newest came 15 months ago, in August 2025, for gpt-oss-20b.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Qwen3-14B (#139).
  • Pass Headroom The best is 21.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on aclanthology.org: 7 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