Model comparison

GPT-5.2 Pro vs GPT-5.4 nano

GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 41.9 on the Noometry Index. GPT-5.4 nano costs 125× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.

Last verified October 12, 2026. 6 shared benchmarks.

GPT-5.2 Pro OpenAI

52.3

Rank #39 Reported

GPT-5.4 nano OpenAI

41.9

Rank #125 Confirmed

Summary

They share 6 benchmarks with published results for both. GPT-5.2 Pro scores higher in 2 categories and GPT-5.4 nano in 0 categories; 2 gaps are clear of the uncertainty.
The widest gap is in reasoning, where GPT-5.2 Pro leads 51.5 to 23.7.
The biggest single-benchmark swing is ARC-AGI-2: 54.2% for GPT-5.2 Pro and 5.7% for GPT-5.4 nano.
GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.

Side by side

GPT-5.2 Pro and GPT-5.4 nano specifications
	GPT-5.2 Pro	GPT-5.4 nano
Provider	OpenAI	OpenAI
Noometry Index	52.3	41.9
Released	2025-12-11	2026-03-17
Weights	Proprietary	Proprietary
Context window	400K	400K
Max output	128K	128K
Input $ / M tokens	$21	$0.20
Output $ / M tokens	$168	$1.25
Results tracked	8	40

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

GPT-5.2 Pro: —, GPT-5.4 nano: 43.6 (#84)

Coding benchmarks
Benchmark	GPT-5.2 Pro	GPT-5.4 nano
SciCode	—	46.9%
WeirdML	—	49.2%
LMArena Coding	—	1405
ALE-Bench	—	1,005

Reasoning GPT-5.2 Pro leads

GPT-5.2 Pro: 51.5 (#33), GPT-5.4 nano: 23.7 (#173)

Reasoning benchmarks
Benchmark	GPT-5.2 Pro	GPT-5.4 nano
ARC-AGI-2	54.2%	5.7%
ARC-AGI-1	90.5%	51.5%
Epoch Capabilities Index	155.4	145.81
SimpleBench	57.4%	—
Kagi LLM Benchmark	—	39.7%
NYT Connections (extended)	79.3%	—
CritPt	—	9.3%
Chess Puzzles	—	30%
LMArena Hard Prompts	—	1381
Mystery Game Puzzles	—	9%
DTBench	—	80.3%
LMCA	—	36.9%
ForecastBench	—	57.3

Math GPT-5.2 Pro leads

GPT-5.2 Pro: 65.3 (#29), GPT-5.4 nano: 40.9 (#88)

Math benchmarks
Benchmark	GPT-5.2 Pro	GPT-5.4 nano
FrontierMath (Tiers 1-3)	74%	44.9%
FrontierMath Tier 4	46%	12.2%
FrontierMath Tier 4 (v1)	31.3%	6.3%
OTIS Mock AIME 2024-2025	—	87.8%
ProofBench	—	5%
LMArena Math	—	1406
FrontierMath (Feb 2025 set)	—	25.9%

Knowledge Not comparable

GPT-5.2 Pro: —, GPT-5.4 nano: 41.9 (#103)

Knowledge benchmarks
Benchmark	GPT-5.2 Pro	GPT-5.4 nano
GPQA Diamond	—	78.5%
SimpleQA Verified	—	11.7%
Vectara Hallucination Rate	—	3.1%
LMArena Expert	—	1396

Multimodal Not comparable

GPT-5.2 Pro: —, GPT-5.4 nano: 36.7 (#78)

Multimodal benchmarks
Benchmark	GPT-5.2 Pro	GPT-5.4 nano
LMArena Vision	—	1196

Multilingual Not comparable

GPT-5.2 Pro: —, GPT-5.4 nano: 48.6 (#140)

Multilingual benchmarks
Benchmark	GPT-5.2 Pro	GPT-5.4 nano
LMArena Non-English	—	1359
LMArena Chinese	—	1392
LMArena French	—	1396
LMArena German	—	1367
LMArena Japanese	—	1343
LMArena Korean	—	1320
LMArena Russian	—	1363
LMArena Spanish	—	1371

Instruction Following Not comparable

GPT-5.2 Pro: —, GPT-5.4 nano: 71.9 (#144)

Instruction Following benchmarks
Benchmark	GPT-5.2 Pro	GPT-5.4 nano
LMArena Instruction Following	—	1362

Long Context Not comparable

GPT-5.2 Pro: —, GPT-5.4 nano: 41.6 (#137)

Long Context benchmarks
Benchmark	GPT-5.2 Pro	GPT-5.4 nano
LMArena Longer Query	—	1366

Writing & Preference Not comparable

GPT-5.2 Pro: —, GPT-5.4 nano: 55.7 (#142)

Writing & Preference benchmarks
Benchmark	GPT-5.2 Pro	GPT-5.4 nano
LMArena Text	—	1372
LMArena Creative Writing	—	1314
LMArena Multi-Turn	—	1382

Frequently asked questions

Is GPT-5.2 Pro better than GPT-5.4 nano?

Which is cheaper, GPT-5.2 Pro or GPT-5.4 nano?

GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; GPT-5.2 Pro lists at $21 and $168.

Which has the bigger context window?

Both accept 400K tokens.

How many benchmarks do GPT-5.2 Pro and GPT-5.4 nano share?

6 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and GPT-5.4 nano has 40.