Noometry

Model comparison

GPT-4.1 mini vs GPT-4.5

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.6 on the Noometry Index.

Last verified . 27 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-4.1 mini scores higher in 3 categories and GPT-4.5 in 7 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GPT-4.5 leads 42.2 to 30.6.
  • The biggest single-benchmark swing is Fiction.LiveBench: 44.4% for GPT-4.1 mini and 63.9% for GPT-4.5.

Side by side

GPT-4.1 miniGPT-4.5
ProviderOpenAIOpenAI
Noometry Index33.637.2
Released2025-04-142025-02-27
WeightsProprietaryProprietary
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4742

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

Category by category

Coding GPT-4.5 leads

GPT-4.1 mini: 30.6 (#293), GPT-4.5: 42.2 (#109)

BenchmarkGPT-4.1 miniGPT-4.5
Aider Polyglot32.4%44.9%
WeirdML37.6%39.4%
LMArena Coding13671396
SWE-bench Verified (bash only)23.9%—
SciCode40.4%—
BigCodeBench Instruct48.9%—
LiveBench Coding—75.2%
CadEval16%—

Agentic & Tool Use GPT-4.1 mini leads

GPT-4.1 mini: 33.3 (#55), GPT-4.5: 27.9 (#97)

BenchmarkGPT-4.1 miniGPT-4.5
Berkeley Function Calling Leaderboard50.5%—
Cybench—17.5%

Reasoning GPT-4.5 leads

GPT-4.1 mini: 10.8 (#340), GPT-4.5: 13.9 (#330)

BenchmarkGPT-4.1 miniGPT-4.5
ARC-AGI-20%0.8%
ARC-AGI-13.5%10.3%
LMArena Hard Prompts13491403
Epoch Capabilities Index135.01136.74
SimpleBench—34.5%
Kagi LLM Benchmark48.6%—
CritPt0%—
Chess Puzzles7%—
EnigmaEval—3.2%
LiveBench Reasoning—71.1%
Mystery Game Puzzles7%—
DTBench68.8%—
LiveBench Data Analysis—64.3%
LMCA21.1%—
ForecastBench—61.7
LiveBench—69%

Math GPT-4.5 leads

GPT-4.1 mini: 24.1 (#270), GPT-4.5: 32.6 (#211)

BenchmarkGPT-4.1 miniGPT-4.5
OTIS Mock AIME 2024-202544.7%37.8%
LMArena Math13431412
MATH Level 587.3%78.6%
FrontierMath (Tiers 1-3)6.7%—
Omni-MATH49.1%—
LiveBench Math—69.3%
FrontierMath (Feb 2025 set)4.5%—

Knowledge GPT-4.1 mini leads

GPT-4.1 mini: 34.7 (#194), GPT-4.5: 32.5 (#211)

BenchmarkGPT-4.1 miniGPT-4.5
GPQA Diamond65.8%68.7%
LMArena Expert13381394
Humanity's Last Exam—5.4%
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
Confabulations—13.6%
GPQA (HELM)61.4%—

Multimodal GPT-4.5 leads

GPT-4.1 mini: 35.8 (#82), GPT-4.5: 37.6 (#71)

BenchmarkGPT-4.1 miniGPT-4.5
LMArena Vision11811195
VPCT—45%

Multilingual GPT-4.5 leads

GPT-4.1 mini: 45.7 (#166), GPT-4.5: 52.5 (#83)

BenchmarkGPT-4.1 miniGPT-4.5
LMArena Non-English13181413
LMArena Chinese13291421
LMArena French13581418
LMArena German13511457
LMArena Japanese12901416
LMArena Korean12981392
LMArena Russian13241419
LMArena Spanish1319—

Instruction Following GPT-4.1 mini leads

GPT-4.1 mini: 73.7 (#118), GPT-4.5: 72.6 (#134)

BenchmarkGPT-4.1 miniGPT-4.5
LMArena Instruction Following13331404
LiveBench Instruction Following—72.3%
IFEval90.4%—

Long Context GPT-4.5 leads

GPT-4.1 mini: 31.8 (#275), GPT-4.5: 40.4 (#155)

BenchmarkGPT-4.1 miniGPT-4.5
Fiction.LiveBench44.4%63.9%
LMArena Longer Query13441406

Writing & Preference GPT-4.5 leads

GPT-4.1 mini: 48.6 (#199), GPT-4.5: 56.9 (#134)

BenchmarkGPT-4.1 miniGPT-4.5
LMArena Text13401417
LMArena Creative Writing13001394
EQ-Bench Creative Writing11471258
LMArena Multi-Turn13541444
Short-Story Creative Writing—75.6%
WildBench83.8%—
LiveBench Language—61.5%

Frequently asked questions

Is GPT-4.1 mini better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.6 on the Noometry Index.

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

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 30.6 in the Noometry coding category.

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

27 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper