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 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
HorizonMath Ranking
Higher score ranks better on this benchmark.
| 1 | TE | 7.1% | 100.0% | 3 | C | |
| 2 | BY | 2.0% | 50.0% | 3 | C | |
| 3 | BY | 2.0% | 0.0% | 3 | C |
HorizonMath Score Distribution
A closer view of the leading scores on this benchmark.
HorizonMath Highlights
The leading models and scores on this benchmark.
What is HorizonMath?
What HorizonMath measures and how its scores work.
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. This benchmark is not independently verified and has an evidence level of B.
- Family
- HorizonMath
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- horizonmath|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
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 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.