Noometry

Model comparison

GPT-4.5 vs GPT-5 Nano

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.5 on the Noometry Index.

Last verified . 27 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

GPT-5 Nano OpenAI

33.5

Rank #241 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-4.5 scores higher in 7 categories and GPT-5 Nano in 3 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-4.5 leads 56.9 to 39.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 81.1% for GPT-5 Nano.

Side by side

GPT-4.5GPT-5 Nano
ProviderOpenAIOpenAI
Noometry Index37.233.5
Released2025-02-272025-08-07
WeightsProprietaryProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$0.05
Output $ / M tokens—$0.40
Results tracked4249

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 42.2 (#109), GPT-5 Nano: 33.6 (#254)

BenchmarkGPT-4.5GPT-5 Nano
WeirdML39.4%38.1%
LMArena Coding13961351
SWE-bench Verified (bash only)—34.8%
Aider Polyglot44.9%—
LiveBench Coding75.2%—
ALE-Bench—718.67

Agentic & Tool Use GPT-4.5 leads

GPT-4.5: 27.9 (#97), GPT-5 Nano: 25.8 (#106)

BenchmarkGPT-4.5GPT-5 Nano
Terminal-Bench—21.8%
Berkeley Function Calling Leaderboard—51.5%
Cybench17.5%—

Reasoning GPT-5 Nano leads

GPT-4.5: 13.9 (#330), GPT-5 Nano: 16.3 (#306)

BenchmarkGPT-4.5GPT-5 Nano
ARC-AGI-20.8%2.6%
ARC-AGI-110.3%20.7%
LMArena Hard Prompts14031328
Epoch Capabilities Index136.74139.38
ForecastBench61.759.1
SimpleBench34.5%—
Kagi LLM Benchmark—62.2%
Chess Puzzles—27%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
Mystery Game Puzzles—9%
DTBench—62.7%
LiveBench Data Analysis64.3%—
LMCA—7.9%
LiveBench69%—

Math GPT-4.5 leads

GPT-4.5: 32.6 (#211), GPT-5 Nano: 29.4 (#241)

BenchmarkGPT-4.5GPT-5 Nano
OTIS Mock AIME 2024-202537.8%81.1%
LMArena Math14121317
MATH Level 578.6%95.2%
FrontierMath (Tiers 1-3)—20%
FrontierMath Tier 4—2.4%
ProofBench—12%
Omni-MATH—54.6%
LiveBench Math69.3%—
FrontierMath (Feb 2025 set)—8.3%
FrontierMath Tier 4 (v1)—2.1%

Knowledge GPT-5 Nano leads

GPT-4.5: 32.5 (#211), GPT-5 Nano: 35.9 (#178)

BenchmarkGPT-4.5GPT-5 Nano
GPQA Diamond68.7%69.4%
LMArena Expert13941321
Humanity's Last Exam5.4%—
SimpleQA Verified—11.7%
MMLU-Pro—77.8%
Confabulations13.6%—
Vectara Hallucination Rate—10.5%
GPQA (HELM)—67.9%

Multimodal GPT-4.5 leads

GPT-4.5: 37.6 (#71), GPT-5 Nano: 31.3 (#108)

BenchmarkGPT-4.5GPT-5 Nano
LMArena Vision11951159
VPCT45%37.2%

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), GPT-5 Nano: 45.3 (#172)

BenchmarkGPT-4.5GPT-5 Nano
LMArena Non-English14131313
LMArena Chinese14211356
LMArena German14571327
LMArena Japanese14161226
LMArena Korean13921269
LMArena Russian14191296
LMArena French1418—
LMArena Spanish—1360

Instruction Following GPT-5 Nano leads

GPT-4.5: 72.6 (#134), GPT-5 Nano: 75.0 (#79)

BenchmarkGPT-4.5GPT-5 Nano
LMArena Instruction Following14041306
LiveBench Instruction Following72.3%—
IFEval—93.2%

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), GPT-5 Nano: 31.3 (#281)

BenchmarkGPT-4.5GPT-5 Nano
Fiction.LiveBench63.9%44.4%
LMArena Longer Query14061312

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), GPT-5 Nano: 39.1 (#249)

BenchmarkGPT-4.5GPT-5 Nano
LMArena Text14171320
LMArena Creative Writing13941249
EQ-Bench Creative Writing1258705
LMArena Multi-Turn14441311
Short-Story Creative Writing75.6%—
WildBench—80.6%
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than GPT-5 Nano?

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.5 on the Noometry Index.

Is GPT-4.5 or GPT-5 Nano better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 33.6 in the Noometry coding category.

How many benchmarks do GPT-4.5 and GPT-5 Nano share?

27 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and GPT-5 Nano has 49.

Related comparisons

Go deeper