GPT-5.4 vs GPT-5 nano

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

GPT-5.4 is clearly ahead on the aggregate, 93 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.4's sharpest advantage is in knowledge, where it averages 88 against 71.2. The single biggest benchmark swing on the page is GPQA, 98 to 71.2.

GPT-5.4 is also the more expensive model on tokens at $2.50 input / $15.00 output per 1M tokens, versus $0.05 input / $0.40 output per 1M tokens for GPT-5 nano. That is roughly 37.5x on output cost alone. GPT-5.4 gives you the larger context window at 1.05M, compared with 400K for GPT-5 nano.

Quick Verdict

Pick GPT-5.4 if you want the stronger benchmark profile. GPT-5 nano only becomes the better choice if you want the cheaper token bill.

Knowledge

GPT-5.4

GPT-5.4

88

GPT-5 nano

71.2

99
MMLU
-
98
GPQA
71.2
96
SuperGPQA
-
94
OpenBookQA
-
93
MMLU-Pro
-
48
HLE
-

Coding

GPT-5.4
95
HumanEval
-
84
SWE-bench Verified
-
84
LiveCodeBench
-

Mathematics

GPT-5.4

GPT-5.4

98

GPT-5 nano

85.2

99
AIME 2023
-
99
AIME 2024
-
99
AIME 2025
85.2
96
HMMT Feb 2023
-
98
HMMT Feb 2024
-
97
HMMT Feb 2025
-
97
BRUMO 2025
-
99
MATH-500
-

Reasoning

GPT-5.4
97
SimpleQA
-
94
MuSR
-
97
BBH
-

Instruction Following

GPT-5.4
96
IFEval
-

Multilingual

GPT-5.4
96
MGSM
-

Frequently Asked Questions

Which is better, GPT-5.4 or GPT-5 nano?

GPT-5.4 is ahead overall, 93 to 31. The biggest single separator in this matchup is GPQA, where the scores are 98 and 71.2.

Which is better for knowledge tasks, GPT-5.4 or GPT-5 nano?

GPT-5.4 has the edge for knowledge tasks in this comparison, averaging 88 versus 71.2. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.4 or GPT-5 nano?

GPT-5.4 has the edge for math in this comparison, averaging 98 versus 85.2. Inside this category, AIME 2025 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.