Noometry

Model comparison

GPT-4.1 mini vs GPT-5

GPT-5 is the stronger model overall, scoring 50.9 to 33.6 on the Noometry Index. GPT-4.1 mini costs 4.9× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

Last verified . 44 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

GPT-5 OpenAI

50.9

Rank #45 Confirmed

Summary

  • They share 44 benchmarks with published results for both. GPT-4.1 mini scores higher in 1 category and GPT-5 in 9 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where GPT-5 leads 69.5 to 31.8.
  • The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 65.7% for GPT-5.
  • GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.25 / $10 for GPT-5.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 400K.

Side by side

GPT-4.1 miniGPT-5
ProviderOpenAIOpenAI
Noometry Index33.650.9
Released2025-04-142025-08-07
WeightsProprietaryProprietary
Context window1.05M400K
Max output33K128K
Input $ / M tokens$0.40$1.25
Output $ / M tokens$1.60$10
Results tracked4769

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

Category by category

Coding GPT-5 leads

GPT-4.1 mini: 30.6 (#293), GPT-5: 50.3 (#47)

BenchmarkGPT-4.1 miniGPT-5
SWE-bench Verified (bash only)23.9%65%
Aider Polyglot32.4%88%
SciCode40.4%42.9%
WeirdML37.6%60.7%
LMArena Coding13671436
SWE-bench Verified—73.6%
LMArena WebDev—1418
GSO—6.9%
BigCodeBench Instruct48.9%—
CadEval16%—
ALE-Bench—1,162
AlgoTune—1.67

Agentic & Tool Use Too close to call

GPT-4.1 mini: 33.3 (#55), GPT-5: 33.1 (#56)

BenchmarkGPT-4.1 miniGPT-5
Terminal-Bench—49.6%
Berkeley Function Calling Leaderboard50.5%—
GDPval—34.8%
Remote Labor Index—1.7%
DeepResearch Bench—49.6%
BALROG—32.8%
LMArena Search—1133
METR Time Horizons—69.6%

Reasoning GPT-5 leads

GPT-4.1 mini: 10.8 (#340), GPT-5: 38.3 (#64)

BenchmarkGPT-4.1 miniGPT-5
ARC-AGI-20%9.9%
Kagi LLM Benchmark48.6%72.7%
ARC-AGI-13.5%65.7%
CritPt0%12.6%
Chess Puzzles7%37%
LMArena Hard Prompts13491416
Mystery Game Puzzles7%23%
DTBench68.8%90.7%
LMCA21.1%40%
Epoch Capabilities Index135.01150
SimpleBench—56.7%
EnigmaEval—10.5%
EBR-Bench—12.7%
ForecastBench—61.4

Math GPT-5 leads

GPT-4.1 mini: 24.1 (#270), GPT-5: 55.0 (#44)

BenchmarkGPT-4.1 miniGPT-5
FrontierMath (Tiers 1-3)6.7%55.4%
OTIS Mock AIME 2024-202544.7%91.4%
Omni-MATH49.1%64.7%
LMArena Math13431407
MATH Level 587.3%98.1%
FrontierMath (Feb 2025 set)4.5%32.4%
FrontierMath Tier 4—22%
ProofBench—18%
FrontierMath Tier 4 (v1)—12.5%

Knowledge GPT-5 leads

GPT-4.1 mini: 34.7 (#194), GPT-5: 56.6 (#43)

BenchmarkGPT-4.1 miniGPT-5
GPQA Diamond65.8%86.2%
SimpleQA Verified12.7%50.1%
MMLU-Pro78.3%86.3%
GPQA (HELM)61.4%79.2%
LMArena Expert13381419
Humanity's Last Exam—25.3%
Confabulations—10.3%
Vectara Hallucination Rate—14.7%

Multimodal GPT-5 leads

GPT-4.1 mini: 35.8 (#82), GPT-5: 46.8 (#13)

BenchmarkGPT-4.1 miniGPT-5
LMArena Vision11811232
GeoBench—81%
VPCT—66%

Multilingual GPT-5 leads

GPT-4.1 mini: 45.7 (#166), GPT-5: 51.4 (#110)

BenchmarkGPT-4.1 miniGPT-5
LMArena Non-English13181397
LMArena Chinese13291422
LMArena French13581410
LMArena German13511416
LMArena Japanese12901409
LMArena Korean12981360
LMArena Russian13241406
LMArena Spanish13191399

Instruction Following Too close to call

GPT-4.1 mini: 73.7 (#118), GPT-5: 73.8 (#113)

BenchmarkGPT-4.1 miniGPT-5
IFEval90.4%87.5%
LMArena Instruction Following13331388

Long Context GPT-5 leads

GPT-4.1 mini: 31.8 (#275), GPT-5: 69.5 (#2)

BenchmarkGPT-4.1 miniGPT-5
Fiction.LiveBench44.4%97.2%
LMArena Longer Query13441399

Writing & Preference GPT-5 leads

GPT-4.1 mini: 48.6 (#199), GPT-5: 63.4 (#65)

BenchmarkGPT-4.1 miniGPT-5
LMArena Text13401406
LMArena Creative Writing13001365
EQ-Bench Creative Writing11471627
WildBench83.8%85.7%
LMArena Multi-Turn13541426
Short-Story Creative Writing—86%

Frequently asked questions

Is GPT-4.1 mini better than GPT-5?

GPT-5 is the stronger model overall, scoring 50.9 to 33.6 on the Noometry Index. GPT-4.1 mini costs 4.9× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

Which is cheaper, GPT-4.1 mini or GPT-5?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GPT-5 lists at $1.25 and $10.

Is GPT-4.1 mini or GPT-5 better for coding?

GPT-5 scores higher on coding benchmarks: 50.3 versus 30.6 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 400K.

How many benchmarks do GPT-4.1 mini and GPT-5 share?

44 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-5 has 69.

Related comparisons

Go deeper