Hungarian National High-School Exam
Models answer the 33 questions of the 2023 Hungarian national high school mathematics finals. Answers are graded by hand with the official rubric.
xAI first used this one exam for Grok-1 because it came after training cutoffs, and hand grading makes scores hard to reproduce.
- Level
- School Students, from grade school to high school
- Scored
- Graded by people Human experts grade or compare the outputs.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Grok-1 leads with 59%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Grok-1 59%
- 2
DeepSeek LLM 67B 58%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok-1 | 59% | Nov 2023 | Model card | |
| 2 | DeepSeek LLM 67B | 58% | Jan 2024 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No launch post has listed it since Nov 2023
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 29 Nov 2023 | DeepSeek LLM 67B | Hungarian National High-School Exam | |
| 3 Nov 2023 | Grok-1 | 59 | Hungarian national high school finals in mathematics (1-shot, human-graded) |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 5 Jan 2024 | DeepSeek LLM 67B technical report | 58 | Hungarian National High-School Exam, human-graded score, held-out (Table 9) | Capabilities |
More in Math
- IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
- AIME 2026 In use Models solve the 30 integer-answer problems from the 2026 AIME I and II math competitions. Scored by exact answer match. GPT-5.5 100%
- HMMT 2026 In use Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match. GPT-5.5 98.5%
- MathArena (Apex, IMO, USAMO) In use Evaluates models on newly released math competitions after release. Final-answer or human/LLM-judged proof scores. Claude Opus 4.8 81.3%
- PolyMath In use Models solve 9,000 parallel math problems in 18 languages across four difficulty levels, from school math to frontier math. Final answers are checked.
Qwen3.7-Max 86.5% - USAMO 2026 In use Models write full proofs for the six problems of the 2026 USA Mathematical Olympiad. Judges grade each proof from 0 to 7 against rubrics. GPT-5.5 98.2%