math benchmark
HorizonMath
HorizonMath is an extremely difficult frontier mathematics benchmark designed to test the limits of mathematical reasoning on research-level and competition-beyond problems.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
HorizonMath leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | TE | 7.1% | 100.0% | 3 | C | |
| 2 | BY | 2.0% | 50.0% | 3 | C | |
| 3 | BY | 2.0% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
HorizonMath highlights
The top published results on this benchmark's own scale.
What is HorizonMath?
Definition and scoring fields from the benchmark registry.
HorizonMath is an extremely difficult frontier mathematics benchmark designed to test the limits of mathematical reasoning on research-level and competition-beyond problems.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- HorizonMath
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- horizonmath|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about HorizonMath.
Which model scores highest on HorizonMath?
Hy3 is currently ranked first with 7.1%.
What does HorizonMath measure?
HorizonMath is an extremely difficult frontier mathematics benchmark designed to test the limits of mathematical reasoning on research-level and competition-beyond problems.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.