PolyMATH

PolyMATH - multilingual mathematical reasoning benchmark.

Category

Multilingual

Max Score

—

Score Type

percent

Active

Yes

Model Scores

Scores for PolyMATH

Model Score Date Verified
Qwen3.5-4B
25.28%
01.02.2026 Verified
Qwen3.5-122B-A10B
91.45%
01.02.2026 Verified
Qwen3.5-27B
100.00%
01.02.2026 Unverified
Qwen3.5-35B-A3B
74.72%
01.02.2026 Unverified
Qwen3-235B-A22B
58.74%
01.02.2026 Unverified
GPT-5-mini 2025-08-07
85.50%
01.02.2026 Unverified
Gemini-2.5-Flash-Thinking
20.45%
31.07.2025 Verified
Qwen3-30B-A3B
6.69%
29.04.2025 Verified
Qwen3-30B-A3B-Thinking-2507
30.86%
31.07.2025 Verified
Qwen3-Next-80B-A3B-Thinking
44.61%
10.09.2025 Verified
Qwen3-VL-30B-A3B
44.30
04.10.2025 Verified