math benchmark
Beyond AIME Leaderboard
Beyond AIME is a difficult mathematical reasoning benchmark focused on deeper reasoning chains and harder decomposition than standard AIME-style problem sets.
Updated Sep 5, 2026
Models5
Model coverage5
MetricScore
EvidenceB
Beyond AIME Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score88.00% | Percentile100.00% | Participants5 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score87.00% | Percentile75.00% | Participants5 | EvidenceC | Evaluated |
| Rank03 | ModelSA | Score69.10% | Percentile50.00% | Participants5 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score66.90% | Percentile25.00% | Participants5 | EvidenceC | Evaluated |
| Rank05 | ModelSA | Score58.30% | Percentile0.00% | Participants5 | EvidenceC | Evaluated |
Beyond AIME Highlights
The leading models and scores on this benchmark.
Beyond AIME Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Beyond AIME
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Beyond AIME?
What Beyond AIME measures and how its scores work.
Beyond AIME is a mathematical reasoning benchmark.
It measures performance on problems requiring deeper reasoning chains and harder decomposition than standard AIME-style problem sets.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Beyond AIME
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Beyond AIME.
Which model scores highest on Beyond AIME?
Seed 2.1 Turbo is currently ranked first with 88.00%.
What are the top three models on Beyond AIME?
The current leaders are Seed 2.1 Turbo (88.00%), Seed 2.1 Pro (87.00%), and Sarvam-105B (69.10%).
Which Beyond AIME model has the lowest official input price?
Mistral Medium 3.5 has the lowest matched official input price at $1.5 input / $7.5 output per 1M tokens.
Which models are fastest among Beyond AIME results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.