List your company

Mathematical Problem Solving on Apex Shortlist

94.27ScoreSTAR-PólyaMath
23.269241.702160.13578.5679May 19, 2026May 26, 2026Jun 2, 2026Jun 9, 2026Jun 16, 2026Jun 23, 2026Jun 30, 2026

Evaluation results

MethodLinks
STAR-PólyaMathBackbone=all GPT-5.5xh2026.0594.27
GPT-5.5Reasoning Effort=xhigh2026.0593.75
Gemini 3.1 Pro2026.0589.06
DeepSeek-v4-ProReasoning Effort=Max2026.0586.46
Claude Opus 4.6Reasoning Effort=high2026.0585.94
Seed2.0 Prosubset=shortlist2026.0682.1
GPT-5.2 Highsubset=shortlist2026.0680.1
GPT-5.4Reasoning Effort=xhigh2026.0578.12
GPT-5.2Reasoning Effort=high2026.0578.12
Kimi K2.6Reasoning Effort=Think2026.0575.52
GLM 5.12026.0572.4
Gemini-3-FlashTier=High2026.0671.9
Gemini-3-pro Highsubset=shortlist2026.0671.4
DeepSeek-v3.2-Speciale2026.0568.23
Gemini 3 Pro2026.0567.19
Claude Opus 4.7Reasoning Effort=xhigh2026.0563.02
Kimi K2.5Reasoning Effort=Think2026.0558.33
Seed2.0 Lite2026.0652.6
Claude-Opus-4.5subset=shortlist2026.0647.4
GPT-5-miniTier=High2026.0643.4
Seed2.0 Mini2026.0631.1
Claude-Sonnet-4.5subset=shortlist2026.0626