GPT-5.4 Pro vs GPT-5.2-Codex

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

GPT-5.4 Pro is clearly ahead on the aggregate, 94 to 88. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.4 Pro's sharpest advantage is in coding, where it averages 89 against 79. The single biggest benchmark swing on the page is HLE, 50 to 26.

GPT-5.4 Pro is also the more expensive model on tokens at $30.00 input / $180.00 output per 1M tokens, versus $2.00 input / $8.00 output per 1M tokens for GPT-5.2-Codex. That is roughly 22.5x on output cost alone. GPT-5.4 Pro gives you the larger context window at 1.05M, compared with 400K for GPT-5.2-Codex.

Quick Verdict

Pick GPT-5.4 Pro if you want the stronger benchmark profile. GPT-5.2-Codex only becomes the better choice if you want the cheaper token bill.

Knowledge

GPT-5.4 Pro

GPT-5.4 Pro

88.8

GPT-5.2-Codex

81.7

99
MMLU
99
99
GPQA
97
97
SuperGPQA
95
94
OpenBookQA
93
94
MMLU-Pro
80
50
HLE
26

Coding

GPT-5.4 Pro

GPT-5.4 Pro

89

GPT-5.2-Codex

79

95
HumanEval
95
86
SWE-bench Verified
76
86
LiveCodeBench
66

Mathematics

GPT-5.4 Pro

GPT-5.4 Pro

98

GPT-5.2-Codex

96.8

99
AIME 2023
99
99
AIME 2024
99
99
AIME 2025
98
96
HMMT Feb 2023
95
98
HMMT Feb 2024
97
97
HMMT Feb 2025
96
97
BRUMO 2025
96
99
MATH-500
94

Reasoning

GPT-5.4 Pro

GPT-5.4 Pro

96.7

GPT-5.2-Codex

92.7

97
SimpleQA
95
95
MuSR
93
98
BBH
90

Instruction Following

GPT-5.4 Pro

GPT-5.4 Pro

97

GPT-5.2-Codex

92

97
IFEval
92

Multilingual

GPT-5.4 Pro

GPT-5.4 Pro

97

GPT-5.2-Codex

91

97
MGSM
91

Frequently Asked Questions

Which is better, GPT-5.4 Pro or GPT-5.2-Codex?

GPT-5.4 Pro is ahead overall, 94 to 88. The biggest single separator in this matchup is HLE, where the scores are 50 and 26.

Which is better for knowledge tasks, GPT-5.4 Pro or GPT-5.2-Codex?

GPT-5.4 Pro has the edge for knowledge tasks in this comparison, averaging 88.8 versus 81.7. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-5.4 Pro or GPT-5.2-Codex?

GPT-5.4 Pro has the edge for coding in this comparison, averaging 89 versus 79. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.4 Pro or GPT-5.2-Codex?

GPT-5.4 Pro has the edge for math in this comparison, averaging 98 versus 96.8. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GPT-5.4 Pro or GPT-5.2-Codex?

GPT-5.4 Pro has the edge for reasoning in this comparison, averaging 96.7 versus 92.7. Inside this category, BBH is the benchmark that creates the most daylight between them.

Which is better for instruction following, GPT-5.4 Pro or GPT-5.2-Codex?

GPT-5.4 Pro has the edge for instruction following in this comparison, averaging 97 versus 92. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GPT-5.4 Pro or GPT-5.2-Codex?

GPT-5.4 Pro has the edge for multilingual tasks in this comparison, averaging 97 versus 91. Inside this category, MGSM is the benchmark that creates the most daylight between them.

Last updated: March 9, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.