DataLearner logo

OpenAI o3-mini (high) Benchmark Details

OpenAI o3-mini (high) currently shows benchmark results led by HumanEval (1 / 140, score 97.60), MATH (1 / 42, score 97.90), MATH-500 (10 / 46, score 97.90).

Benchmark Results

OpenAI o3-mini (high)

Benchmark Results

Thinking

General Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Standard Mode
86.90
27 / 124
ARC-AGI-1
Standard Mode
34.50
120 / 147

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
HumanEval
Standard Mode
97.60
1 / 140
LiveCodeBench
Standard Mode
69.50
96 / 251
SWE-bench Verified
Standard Mode
49.30
97 / 116

Math and Reasoning

5 evaluations
Benchmark / mode
Score
Rank/total
MATH
Standard Mode
97.90
1 / 42
MATH-500
Standard Mode
97.90
10 / 46
AIME 2024
Standard Mode
87
18 / 62
FrontierMath
Thinking Level · High
11
23 / 60
FrontierMath - Tier 4
Thinking Level · High
4.20
40 / 80

Other

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
79.70
241 / 463

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
Standard Mode
13.80
37 / 47
Compare with other models