DataLearner logo

GPT-4o Benchmark Details

GPT-4o currently shows benchmark results led by HumanEval (8 / 39, score 90), MMLU (15 / 66, score 88.70), BBH (5 / 21, score 91.70).

Benchmark Results

GPT-4o

Benchmark Results

Thinking
Tool usage

General Knowledge

5 evaluations
Benchmark / mode
Score
Rank/total
BBH
91.70
5 / 21
MMLU
88.70
15 / 66
MMLU Pro
77.90
75 / 132
GPQA Diamond
70.10
119 / 187
HLE
5.30
162 / 170

Coding and Software Engineer

4 evaluations
Benchmark / mode
Score
Rank/total
HumanEval
90
8 / 39
LiveCodeBench
35.10
108 / 123
SWE-bench Verified
31
106 / 111
IC SWE-Lancer(Diamond)
23.30
6 / 8

Math and Reasoning

5 evaluations
Benchmark / mode
Score
Rank/total
MATH
75.90
16 / 42
MATH-500
75.90
43 / 44
AIME2025
42.10
94 / 107
AIME 2024
9.30
61 / 62
FrontierMath
0.30
57 / 60

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
38.20
22 / 47

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Standard Mode
23.10
47 / 59

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
Pinch Bench
Thinking EnabledTools
71.10
30 / 37
Compare with other models