Noometry

Model comparison

GPT-4.1 mini vs GPT-5 Mini

GPT-5 Mini is the stronger model overall, scoring 41.8 to 33.6 on the Noometry Index.

Last verified . 44 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

GPT-5 Mini OpenAI

41.8

Rank #128 Confirmed

Summary

  • They share 44 benchmarks with published results for both. GPT-4.1 mini scores higher in 2 categories and GPT-5 Mini in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5 Mini leads 46.7 to 24.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 54.3% for GPT-5 Mini.
  • Both cost about the same: $0.40 input and $1.60 output per million tokens.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 400K.

Side by side

GPT-4.1 miniGPT-5 Mini
ProviderOpenAIOpenAI
Noometry Index33.641.8
Released2025-04-142025-08-07
WeightsProprietaryProprietary
Context window1.05M400K
Max output33K128K
Input $ / M tokens$0.40$0.25
Output $ / M tokens$1.60$2
Results tracked4760

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

Category by category

Coding GPT-5 Mini leads

GPT-4.1 mini: 30.6 (#293), GPT-5 Mini: 40.1 (#146)

BenchmarkGPT-4.1 miniGPT-5 Mini
SWE-bench Verified (bash only)23.9%59.8%
SciCode40.4%39.2%
WeirdML37.6%52.7%
LMArena Coding13671406
SWE-bench Verified—64.7%
Aider Polyglot32.4%—
SWE-bench Multilingual—39.7%
BigCodeBench Instruct48.9%—
CadEval16%—
ALE-Bench—799.77
AlgoTune—1.38

Agentic & Tool Use GPT-4.1 mini leads

GPT-4.1 mini: 33.3 (#55), GPT-5 Mini: 31.1 (#70)

BenchmarkGPT-4.1 miniGPT-5 Mini
Berkeley Function Calling Leaderboard50.5%55.5%
Terminal-Bench—34.8%
Vending-Bench 2—-31.18

Reasoning GPT-5 Mini leads

GPT-4.1 mini: 10.8 (#340), GPT-5 Mini: 23.9 (#168)

BenchmarkGPT-4.1 miniGPT-5 Mini
ARC-AGI-20%4.4%
Kagi LLM Benchmark48.6%70.3%
ARC-AGI-13.5%54.3%
CritPt0%0%
Chess Puzzles7%30%
LMArena Hard Prompts13491380
Mystery Game Puzzles7%10%
DTBench68.8%80.5%
LMCA21.1%34.2%
Epoch Capabilities Index135.01145.52
EnigmaEval—8.2%
ForecastBench—61

Math GPT-5 Mini leads

GPT-4.1 mini: 24.1 (#270), GPT-5 Mini: 46.7 (#69)

BenchmarkGPT-4.1 miniGPT-5 Mini
FrontierMath (Tiers 1-3)6.7%46.7%
OTIS Mock AIME 2024-202544.7%86.7%
Omni-MATH49.1%72.2%
LMArena Math13431378
MATH Level 587.3%97.8%
FrontierMath (Feb 2025 set)4.5%27.2%
FrontierMath Tier 4—12.2%
ProofBench—9%
FrontierMath Tier 4 (v1)—6.3%

Knowledge GPT-5 Mini leads

GPT-4.1 mini: 34.7 (#194), GPT-5 Mini: 45.6 (#86)

BenchmarkGPT-4.1 miniGPT-5 Mini
GPQA Diamond65.8%75%
SimpleQA Verified12.7%21.6%
MMLU-Pro78.3%83.5%
GPQA (HELM)61.4%75.6%
LMArena Expert13381379
Humanity's Last Exam—19.4%
Confabulations—13.3%
Vectara Hallucination Rate—12.9%

Multimodal Too close to call

GPT-4.1 mini: 35.8 (#82), GPT-5 Mini: 35.6 (#85)

BenchmarkGPT-4.1 miniGPT-5 Mini
LMArena Vision11811202
VPCT—40.2%

Multilingual GPT-5 Mini leads

GPT-4.1 mini: 45.7 (#166), GPT-5 Mini: 48.9 (#137)

BenchmarkGPT-4.1 miniGPT-5 Mini
LMArena Non-English13181363
LMArena Chinese13291385
LMArena French13581386
LMArena German13511366
LMArena Japanese12901341
LMArena Korean12981308
LMArena Russian13241362
LMArena Spanish13191355

Instruction Following GPT-5 Mini leads

GPT-4.1 mini: 73.7 (#118), GPT-5 Mini: 76.2 (#46)

BenchmarkGPT-4.1 miniGPT-5 Mini
IFEval90.4%92.7%
LMArena Instruction Following13331357

Long Context GPT-5 Mini leads

GPT-4.1 mini: 31.8 (#275), GPT-5 Mini: 41.9 (#132)

BenchmarkGPT-4.1 miniGPT-5 Mini
Fiction.LiveBench44.4%69.4%
LMArena Longer Query13441355

Writing & Preference GPT-5 Mini leads

GPT-4.1 mini: 48.6 (#199), GPT-5 Mini: 55.2 (#148)

BenchmarkGPT-4.1 miniGPT-5 Mini
LMArena Text13401373
LMArena Creative Writing13001325
EQ-Bench Creative Writing11471313
WildBench83.8%85.5%
LMArena Multi-Turn13541363
Short-Story Creative Writing—83.1%

Frequently asked questions

Is GPT-4.1 mini better than GPT-5 Mini?

GPT-5 Mini is the stronger model overall, scoring 41.8 to 33.6 on the Noometry Index.

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

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.

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

GPT-5 Mini scores higher on coding benchmarks: 40.1 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 Mini share?

44 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-5 Mini has 60.

Related comparisons

Go deeper