Noometry

Model comparison

GPT-4.1 nano vs GPT-4.5

GPT-4.5 is the stronger model overall, scoring 36.9 to 27.7 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-4.1 nano OpenAI

27.7

Rank #322 Confirmed

GPT-4.5 OpenAI

36.9

Rank #200 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and GPT-4.5 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GPT-4.5 leads 41.8 to 23.8.
  • The biggest single-benchmark swing is Fiction.LiveBench: 25% for GPT-4.1 nano and 63.9% for GPT-4.5.

Side by side

GPT-4.1 nanoGPT-4.5
ProviderOpenAIOpenAI
Noometry Index27.736.9
Released2025-04-142025-02-27
WeightsProprietaryProprietary
Context window1.05M—
Max output33K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.40—
Results tracked3842

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

Category by category

Coding GPT-4.5 leads

GPT-4.1 nano: 23.8 (#325), GPT-4.5: 41.8 (#102)

BenchmarkGPT-4.1 nanoGPT-4.5
Aider Polyglot8.9%44.9%
WeirdML19%39.4%
LMArena Coding13061397
SciCode25.9%—
LiveBench Coding—75.2%

Agentic & Tool Use GPT-4.5 leads

GPT-4.1 nano: 26.3 (#98), GPT-4.5: 27.6 (#92)

BenchmarkGPT-4.1 nanoGPT-4.5
Berkeley Function Calling Leaderboard33%—
Cybench—17.5%

Reasoning GPT-4.5 leads

GPT-4.1 nano: 8.6 (#344), GPT-4.5: 14.1 (#320)

BenchmarkGPT-4.1 nanoGPT-4.5
ARC-AGI-20%0.8%
ARC-AGI-10%10.3%
LMArena Hard Prompts12861404
Epoch Capabilities Index129.62136.74
SimpleBench—34.5%
Kagi LLM Benchmark33.3%—
CritPt0%—
EnigmaEval—3.2%
LiveBench Reasoning—71.1%
DTBench52.5%—
LiveBench Data Analysis—64.3%
LMCA5.5%—
ForecastBench—61.7
LiveBench—69%

Math GPT-4.5 leads

GPT-4.1 nano: 25.5 (#246), GPT-4.5: 31.0 (#200)

BenchmarkGPT-4.1 nanoGPT-4.5
OTIS Mock AIME 2024-202528.9%37.8%
LMArena Math12741412
MATH Level 570%78.6%
Omni-MATH36.7%—
LiveBench Math—69.3%
FrontierMath (Feb 2025 set)1%—

Knowledge GPT-4.5 leads

GPT-4.1 nano: 21.8 (#268), GPT-4.5: 32.4 (#205)

BenchmarkGPT-4.1 nanoGPT-4.5
GPQA Diamond48.9%68.7%
LMArena Expert12721394
Humanity's Last Exam—5.4%
SimpleQA Verified6%—
MMLU-Pro55%—
Confabulations—13.6%
GPQA (HELM)50.7%—

Multimodal GPT-4.5 leads

GPT-4.1 nano: 28.6 (#108), GPT-4.5: 37.0 (#68)

BenchmarkGPT-4.1 nanoGPT-4.5
LMArena Vision10631195
VPCT—45%

Multilingual GPT-4.5 leads

GPT-4.1 nano: 41.8 (#200), GPT-4.5: 52.7 (#78)

BenchmarkGPT-4.1 nanoGPT-4.5
LMArena Non-English12601413
LMArena Chinese12701421
LMArena German12881457
LMArena Japanese11991416
LMArena Russian12611419
LMArena French—1417
LMArena Korean—1392

Instruction Following GPT-4.5 leads

GPT-4.1 nano: 68.0 (#188), GPT-4.5: 72.8 (#129)

BenchmarkGPT-4.1 nanoGPT-4.5
LMArena Instruction Following12671404
LiveBench Instruction Following—72.3%
IFEval84.3%—

Long Context GPT-4.5 leads

GPT-4.1 nano: 23.7 (#291), GPT-4.5: 40.4 (#150)

BenchmarkGPT-4.1 nanoGPT-4.5
Fiction.LiveBench25%63.9%
LMArena Longer Query12831406

Writing & Preference GPT-4.5 leads

GPT-4.1 nano: 40.7 (#238), GPT-4.5: 57.1 (#129)

BenchmarkGPT-4.1 nanoGPT-4.5
LMArena Text12851417
LMArena Creative Writing12601394
EQ-Bench Creative Writing9461258
LMArena Multi-Turn12771444
Short-Story Creative Writing—75.6%
WildBench81.2%—
LiveBench Language—61.5%

Frequently asked questions

Is GPT-4.1 nano better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 36.9 to 27.7 on the Noometry Index.

Is GPT-4.1 nano or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 23.8 in the Noometry coding category.

How many benchmarks do GPT-4.1 nano and GPT-4.5 share?

25 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper