Benchmark Almanac

PalmX 2025 General Culture

Human-centred AI (HAI) research group 72.2% tops its leaderboard
Not in model cards

Models choose answers about customs, history and daily life across Arab countries. The test contains 2,000 questions in Modern Standard Arabic.

The organizers ranked nine team systems. The winning team fine-tuned NileChat-3B and scored 72.15% accuracy.

Released
June 2025
Kind
Knowledge in many languages
Level
School
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
9
Entries on its own leaderboard, 0 models we track

Human-centred AI (HAI) research group tops the leaderboard with 72.2%

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 Human-centred AI (HAI) research group 72.2%
  2. 2 Pulkit Chatwal 71.7%
  3. 3 AYA_Team 71.5%
  4. 4 Phoenix 71.3%
  5. 5 CultranAI 70.5%
  6. 6 ISL-NLP 67.6%
  7. 7 Rafiul Biswas 67.5%
  8. 8 Hamyaria 65.9%
  9. 9 Star 64%

Source: Official PalmX 2025 General Culture leaderboard

#EntryScoreSettingSubmitted byAgent byDateSource
1 Human-centred AI (HAI) research group 72.2% Shehenaz Hossain, Haithem Afli, Mohammmed Hasanuzzaman ADAPT, MTU Official leaderboard
2 Pulkit Chatwal 71.7% Pulkit Chatwal Institute of Petroleum Technology Official leaderboard
3 AYA_Team 71.5% Jannatul tajrin, Bir Ballav Roy QCRI Official leaderboard
4 Phoenix 71.3% Houdaifa atou, AtouIssam Ait Yahia, Ismail Berrada Mohammed VI Polytechnic University Official leaderboard
5 CultranAI 70.5% Youssef Ahmed, Hunzalah Hassan, Firoj Alam HBKU Official leaderboard
6 ISL-NLP 67.6% Mohamed Gomaa, Nour Eldian Arab Academy for Science and Technology (AAST) Official leaderboard
7 Rafiul Biswas 67.5% Shimaa Ibrahim, Kais Attia, Rafiul Biswas, Mabrouka Bessghaier, Wajdi Zaghouani Hamad Bin Khalifa University Official leaderboard
8 Hamyaria 65.9% Walid Al-Dhabyani, Hamzah A. Alsayadi Hadhramout University, Cairo University Official leaderboard
9 Star 64% Eman Elrefai, Esraa Fouad, Hassan Ehab Alexandria 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 Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

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 (9 entries).
  • Pass Models scored 9 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 palmx.dlnlp.ai: 9 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