Benchmark Almanac

Hungarian Riddles Benchmark

GPT-5 67.7% leads since October 2025
Not in model cards

Models answer 100 original Hungarian riddles and justify each answer in Hungarian. The author grades factual accuracy, reasoning, and language.

The pilot table covers five model families in six configurations. CulturalRiddles later expanded the pilot to 62 communities.

Made by
Károly Boczka
Released
October 2025
Kind
Reasoning in many languages
Level
Everyday
Scored
Graded by people
Answers
Short answer
Tasks
All public
Measures
Capability
Language
Hungarian
In and out
Text → Text
Interaction
Single turn
Items from
Written by experts
Run by
Anyone
Strongest model tested
GPT-5 #71 on the capability index
Last model added
September 2025
Scores refreshed
November 20th, 2026
5
Entries on its own leaderboard, 4 models we track

GPT-5 leads with 67.7% among models released by September 2025 GPT-5 leads with 67.7% among models released by September 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 September 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 GPT-5 Deep Search 67.7%
  2. 2 Gemini 2.5 Flash Sep 2025 55.9%
  3. 3 Claude Sonnet 4 41.5%
  4. 4 Grok 35.5%
  5. 5 DeepSeek-R1 May 2025 33.5%

Source: Official Hungarian Riddles Benchmark leaderboard

#EntryScoreSettingDateSource
1 GPT-5 67.7% Deep Search Aug 2025 Official leaderboard
2 Gemini 2.5 Flash Sep 2025 55.9% Sep 2025 Official leaderboard
3 Claude Sonnet 4 41.5% May 2025 Official leaderboard
4 Grok 35.5% Official leaderboard
5 DeepSeek-R1 May 2025 33.5% May 2025 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5 67.7% Deep Search Aug 2025 Official leaderboard
2 Gemini 2.5 Flash Sep 2025 55.9% Sep 2025 Official leaderboard
3 Claude Sonnet 4 41.5% May 2025 Official leaderboard
4 DeepSeek-R1 May 2025 33.5% May 2025 Official leaderboard

Number one over time

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

OpenAI
Own leaderboard Not tested since Oct 2025
GPT-5 67.7%

Source: Official Hungarian Riddles Benchmark 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 Near the ceiling (85%) GPT-5 Claude Sonnet 4 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-5 Claude Sonnet 4

Source: Official Hungarian Riddles Benchmark 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.

Versions

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 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (5 entries).
  • Pass Models scored 4 models we track, plus 1 other entry on its leaderboard.
  • Note Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. That’s expected for a test replaced by CulturalRiddles.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5 (#71).
  • Pass Headroom The best is 67.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 5 rows for models we track and 1 other entry 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