math benchmark
FrontierMath Tier 4 (v2)
FrontierMath Tier 4 subset from the v2 evaluation release.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
FrontierMath Tier 4 (v2) Ranking
Higher score ranks better on this benchmark.
| 1 | OP | 83.0% | 100.0% | 3 | C | |
| 2 | OP | 68.3% | 50.0% | 3 | C | |
| 3 | OP | 58.5% | 0.0% | 3 | C |
FrontierMath Tier 4 (v2) Score Distribution
A closer view of the leading scores on this benchmark.
FrontierMath Tier 4 (v2) Highlights
The leading models and scores on this benchmark.
What is FrontierMath Tier 4 (v2)?
What FrontierMath Tier 4 (v2) measures and how its scores work.
FrontierMath Tier 4 subset from the v2 evaluation release.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- FrontierMath Tier 4 (v2)
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- frontiermath-tier-4-v2|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about FrontierMath Tier 4 (v2).
Which model scores highest on FrontierMath Tier 4 (v2)?
GPT-5.6 Sol is currently ranked first with 83.0%.
What does FrontierMath Tier 4 (v2) measure?
FrontierMath Tier 4 subset from the v2 evaluation release.
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.