o3-pro Benchmark Details

o3-pro currently shows benchmark results led by Aider-Polyglot (3 / 59, score 84.90), AIME 2024 (8 / 62, score 93), AIME2025 (31 / 107, score 93).

Benchmark Results

o3-pro

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

59 / 187

ARC-AGI

59.30

37 / 67

HLE

113 / 170

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

37 / 111

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

AIME 2024

8 / 62

AIME2025

31 / 107

Agent Level Benchmark

1 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Thinking Level · High

84.90

3 / 59

AI Agent - Tool Usage

1 evaluations

Benchmark / mode

Score

Rank/total

MCP-Atlas

Standard ModeTools

44.50

26 / 27

Compare with other models