math benchmark
PolyMath-en Leaderboard
PolyMath-en is a multilingual mathematical reasoning benchmark covering 18 languages and 4 difficulty levels from easy to hard.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
PolyMath-en Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score65.10% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score65.10% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
PolyMath-en Highlights
The leading models and scores on this benchmark.
PolyMath-en Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for PolyMath-en
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is PolyMath-en?
What PolyMath-en measures and how its scores work.
PolyMath-en is a multilingual benchmark for evaluating the mathematical reasoning capabilities of large language models across diverse linguistic contexts.
It measures mathematical reasoning using the Score metric, reported as a ratio, across 18 languages and 4 difficulty levels from easy to hard.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- PolyMath-en
- 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 PolyMath-en.
Which model scores highest on PolyMath-en?
Kimi K2 Instruct is currently ranked first with 65.10%.
What are the top three models on PolyMath-en?
The current leaders are Kimi K2 Instruct (65.10%) and Kimi K2-Instruct-0905 (65.10%).
Which PolyMath-en model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among PolyMath-en 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.