List your company

Mathematical Problem Solving on Apex 2025 (Score %)

93.75ScoreSTAR-PólyaMath
5.45428.37751.374.223May 19, 2026

Evaluation results

MethodLinks
STAR-PólyaMathBackbone=all GPT-5.5xh2026.0593.75
GPT-5.5Reasoning Effort=xhigh2026.0580.21
Gemini 3.1 Pro2026.0560.94
GPT-5.4Reasoning Effort=xhigh2026.0554.17
Claude Opus 4.7Reasoning Effort=xhigh2026.0540.62
Claude Opus 4.6Reasoning Effort=high2026.0534.45
DeepSeek-v4-ProReasoning Effort=Max2026.0528.12
Kimi K2.6Reasoning Effort=Think2026.0523.96
Gemini 3 Pro2026.0523.44
GPT-5.2Reasoning Effort=high2026.0513.54
GLM 5.12026.0511.46
DeepSeek-v3.2-Speciale2026.059.38
Kimi K2.5Reasoning Effort=Think2026.058.85