Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on Apex 2025 (Score %)
Loading...
93.75
Score
STAR-PólyaMath
5.454
28.377
51.3
74.223
May 19, 2026
Score
Updated 14d ago
Evaluation Results
Method
Method
Links
Score
STAR-PólyaMath
Backbone=all GPT-5.5xh
2026.05
93.75
GPT-5.5
Reasoning Effort=xhigh
2026.05
80.21
Gemini 3.1 Pro
2026.05
60.94
GPT-5.4
Reasoning Effort=xhigh
2026.05
54.17
Claude Opus 4.7
Reasoning Effort=xhigh
2026.05
40.62
Claude Opus 4.6
Reasoning Effort=high
2026.05
34.45
DeepSeek-v4-Pro
Reasoning Effort=Max
2026.05
28.12
Kimi K2.6
Reasoning Effort=Think
2026.05
23.96
Gemini 3 Pro
2026.05
23.44
GPT-5.2
Reasoning Effort=high
2026.05
13.54
GLM 5.1
2026.05
11.46
DeepSeek-v3.2-Speciale
2026.05
9.38
Kimi K2.5
Reasoning Effort=Think
2026.05
8.85
Feedback
Search any
task
Search any
task