GPT-5 (high) Benchmark Scores & Performance

Benchmark analysis of GPT-5 (high) by OpenAI across 14 tests.

Creator

OpenAI

Source Type

Proprietary

Reasoning

Reasoning

Context Window

128K

Overall Score

72#17 of 88

Knowledge Benchmarks

MMLU
93
GPQA
91
SuperGPQA
89
OpenBookQA
87

Coding Benchmarks

HumanEval
85

Mathematics Benchmarks

AIME 2023
95
AIME 2024
97
AIME 2025
96
HMMT Feb 2023
91
HMMT Feb 2024
93
HMMT Feb 2025
92
BRUMO 2025
94

Reasoning Benchmarks

SimpleQA
89
MuSR
87

Frequently Asked Questions

How does GPT-5 (high) perform overall in AI benchmarks?

GPT-5 (high) ranks #17 out of 88 models with an overall score of 72. It is created by OpenAI and features a 128K context window.

Is GPT-5 (high) good for knowledge and understanding?

GPT-5 (high) ranks #17 out of 88 models in knowledge and understanding benchmarks with an average score of 90. There are stronger options in this category.

Is GPT-5 (high) good for coding and programming?

GPT-5 (high) ranks #18 out of 88 models in coding and programming benchmarks with an average score of 85. There are stronger options in this category.

Is GPT-5 (high) good for mathematics?

GPT-5 (high) ranks #17 out of 88 models in mathematics benchmarks with an average score of 94. There are stronger options in this category.

Is GPT-5 (high) good for reasoning and logic?

GPT-5 (high) ranks #17 out of 88 models in reasoning and logic benchmarks with an average score of 88. There are stronger options in this category.

What is the context window size of GPT-5 (high)?

GPT-5 (high) has a context window of 128K tokens, which determines how much text it can process in a single interaction.