Noometry

Model comparison

GPT-4 vs GPT-4.1 mini

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 29.1 on the Noometry Index.

Last verified . 28 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Summary

  • They share 28 benchmarks with published results for both. GPT-4 scores higher in 3 categories and GPT-4.1 mini in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.1 mini leads 34.7 to 18.4.
  • The biggest single-benchmark swing is MATH Level 5: 23% for GPT-4 and 87.3% for GPT-4.1 mini.
  • GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $30 / $60 for GPT-4.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 8K.

Side by side

GPT-4GPT-4.1 mini
ProviderOpenAIOpenAI
Noometry Index29.133.6
Released2023-03-142025-04-14
WeightsProprietaryProprietary
Context window8K1.05M
Max output8K33K
Input $ / M tokens$30$0.40
Output $ / M tokens$60$1.60
Results tracked3847

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

Category by category

Coding Too close to call

GPT-4: 31.6 (#283), GPT-4.1 mini: 30.6 (#293)

BenchmarkGPT-4GPT-4.1 mini
WeirdML12.4%37.6%
BigCodeBench Instruct46%48.9%
LMArena Coding12541367
SWE-bench Verified (bash only)—23.9%
Aider Polyglot—32.4%
SciCode—40.4%
BigCodeBench Complete57.2%—
CadEval—16%
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, GPT-4.1 mini: 33.3 (#55)

BenchmarkGPT-4GPT-4.1 mini
Berkeley Function Calling Leaderboard—50.5%
METR Time Horizons36.1%—

Reasoning GPT-4 leads

GPT-4: 17.8 (#289), GPT-4.1 mini: 10.8 (#340)

BenchmarkGPT-4GPT-4.1 mini
Chess Puzzles4%7%
LMArena Hard Prompts12411349
Mystery Game Puzzles12%7%
DTBench62.7%68.8%
LMCA17.1%21.1%
Epoch Capabilities Index125.89135.01
ARC-AGI-2—0%
Kagi LLM Benchmark—48.6%
ARC-AGI-1—3.5%
CritPt—0%
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math GPT-4.1 mini leads

GPT-4: 10.8 (#309), GPT-4.1 mini: 24.1 (#270)

BenchmarkGPT-4GPT-4.1 mini
OTIS Mock AIME 2024-20251.1%44.7%
LMArena Math12691343
MATH Level 523%87.3%
FrontierMath (Tiers 1-3)—6.7%
Omni-MATH—49.1%
FrontierMath (Feb 2025 set)—4.5%
GSM8K92%—

Knowledge GPT-4.1 mini leads

GPT-4: 18.4 (#282), GPT-4.1 mini: 34.7 (#194)

BenchmarkGPT-4GPT-4.1 mini
GPQA Diamond35.7%65.8%
LMArena Expert12111338
SimpleQA Verified—12.7%
MMLU-Pro—78.3%
GPQA (HELM)—61.4%
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, GPT-4.1 mini: 35.8 (#82)

BenchmarkGPT-4GPT-4.1 mini
LMArena Vision—1181

Multilingual GPT-4.1 mini leads

GPT-4: 40.6 (#215), GPT-4.1 mini: 45.7 (#166)

BenchmarkGPT-4GPT-4.1 mini
LMArena Non-English12461318
LMArena Chinese12421329
LMArena French12831358
LMArena German12511351
LMArena Japanese12091290
LMArena Korean11841298
LMArena Russian12511324
LMArena Spanish12611319

Instruction Following GPT-4.1 mini leads

GPT-4: 65.3 (#222), GPT-4.1 mini: 73.7 (#118)

BenchmarkGPT-4GPT-4.1 mini
LMArena Instruction Following12411333
IFEval—90.4%

Long Context GPT-4 leads

GPT-4: 37.7 (#212), GPT-4.1 mini: 31.8 (#275)

BenchmarkGPT-4GPT-4.1 mini
LMArena Longer Query12441344
Fiction.LiveBench—44.4%

Writing & Preference GPT-4.1 mini leads

GPT-4: 34.9 (#268), GPT-4.1 mini: 48.6 (#199)

BenchmarkGPT-4GPT-4.1 mini
LMArena Text12631340
LMArena Creative Writing12441300
EQ-Bench Creative Writing7521147
LMArena Multi-Turn12571354
WildBench—83.8%

Frequently asked questions

Is GPT-4 better than GPT-4.1 mini?

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or GPT-4.1 mini?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or GPT-4.1 mini better for coding?

They score almost the same on coding (31.6 vs 30.6); test both on your own repository before choosing.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 8K.

How many benchmarks do GPT-4 and GPT-4.1 mini share?

28 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and GPT-4.1 mini has 47.

Related comparisons

Go deeper