PolyMath
We show this table for reference; we do not rank on it.
A multilingual mathematical reasoning benchmark that tests whether math performance transfers across languages rather than only in English.
Benchmark score on PolyMath — November 13, 2026
We compile the PolyMath rows from provider self-reports and secondary reports. Qwen3.7 Max leads the table at 86.5%, followed by Qwen3.7 Plus (84.0%) and Claude Opus 4.5 (79.0%). We do not use these results to rank models overall.
Qwen3.7 Max
Alibaba
Reported by AlibabaQwen3.7 Plus
Alibaba
Reported by AlibabaClaude Opus 4.5
Anthropic
Another lab’s comparison table6 modelsMultilingualCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (6 models)
None of the 6 results on this page has a documented run by the benchmark or an independent evaluator: 4 reported by the labs that built the models and 2 reported in another publisher’s document.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Qwen3.7 MaxAlibabaReported by Alibaba | 86.5% | Reported by Alibaba | Not reported | Closed |
| 2 | Qwen3.7 PlusAlibabaReported by Alibaba | 84.0% | Reported by Alibaba | Not reported | Closed |
| 3 | Claude Opus 4.5AnthropicAnother lab’s comparison table | 79.0% | Another lab’s comparison table | Not reported | Closed |
| 4 | Qwen3.5 397BAlibabaReported by Alibaba | 73.3% | Reported by Alibaba | Not reported | Open |
| 5 | K-EXAONE 2.0LG AI ResearchReported by LG AI Research | 71.3% | Reported by LG AI Research | Not reported | Open |
| 6 | Kimi K2.5Moonshot AIAnother lab’s comparison table | 43.1% | Another lab’s comparison table | Not reported | Open |
- Lab-reported
- Benchmark-run
- Independent
Among the reported PolyMath rows, Qwen3.7 Max is first at 86.5%. The third row is 7.5 points behind. The broader top-10 range is 43.4 points, so the table still separates the published systems.
6 models have been evaluated on PolyMath. The benchmark falls in the Multilingual category. PolyMath is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About PolyMath
Year
2026
Tasks
Multilingual math problems
Format
Cross-lingual mathematical reasoning
Difficulty
Advanced multilingual reasoning
PolyMath isolates cross-lingual math transfer rather than general chat quality. It is useful for spotting models that keep surface fluency in other languages but lose structured reasoning quality.
Freshness and provenance
Version
PolyMath 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does PolyMath measure?
A multilingual mathematical reasoning benchmark that tests whether math performance transfers across languages rather than only in English.
Which model scores highest on PolyMath?
Qwen3.7 Max by Alibaba currently leads with a score of 86.5% on PolyMath.
How many models are evaluated on PolyMath?
6 AI models have published results on PolyMath in the BenchLM catalog.
Compare top models on PolyMath
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.