Benchmark
HorizonMath Benchmark
What is HorizonMath?
Unsolved research-level mathematics, reported at pass@4, so figures sit far below conventional accuracy scales.
- Evaluates
- math
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 1
Source provenance
- Original evidence https://github.com/ewang26/HorizonMath
HorizonMath code
HorizonMath results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Hy4 preview | Tencent | 8.8 | 2026-08-28 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite HorizonMath?
- Hy4 preview Tencent, 2026-08-28