Noometry

Model comparison

GPT-4 vs GPT-4.1 nano

GPT-4 is the stronger model overall, scoring 28.9 to 27.7 on the Noometry Index. GPT-4.1 nano costs 214× less per token, which makes it the better buy when GPT-4's lead doesn't matter for your workload.

Last verified . 22 shared benchmarks.

GPT-4 OpenAI

28.9

Rank #308 Confirmed

GPT-4.1 nano OpenAI

27.7

Rank #322 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GPT-4 scores higher in 3 categories and GPT-4.1 nano in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-4.1 nano leads 25.5 to 10.1.
  • The biggest single-benchmark swing is MATH Level 5: 23% for GPT-4 and 70% for GPT-4.1 nano.
  • GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $30 / $60 for GPT-4.
  • GPT-4.1 nano accepts more context: 1.05M tokens versus 8K.

Side by side

GPT-4GPT-4.1 nano
ProviderOpenAIOpenAI
Noometry Index28.927.7
Released2023-03-142025-04-14
WeightsProprietaryProprietary
Context window8K1.05M
Max output8K33K
Input $ / M tokens$30$0.10
Output $ / M tokens$60$0.40
Results tracked3838

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

Category by category

Coding GPT-4 leads

GPT-4: 31.2 (#277), GPT-4.1 nano: 23.8 (#325)

BenchmarkGPT-4GPT-4.1 nano
WeirdML12.4%19%
LMArena Coding12541306
Aider Polyglot—8.9%
SciCode—25.9%
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, GPT-4.1 nano: 26.3 (#98)

BenchmarkGPT-4GPT-4.1 nano
Berkeley Function Calling Leaderboard—33%
METR Time Horizons36.1%—

Reasoning GPT-4 leads

GPT-4: 17.3 (#285), GPT-4.1 nano: 8.6 (#344)

BenchmarkGPT-4GPT-4.1 nano
LMArena Hard Prompts12411286
DTBench62.7%52.5%
LMCA17.1%5.5%
Epoch Capabilities Index125.88129.62
ARC-AGI-2—0%
Kagi LLM Benchmark—33.3%
ARC-AGI-1—0%
CritPt—0%
Chess Puzzles4%—
Mystery Game Puzzles12%—
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math GPT-4.1 nano leads

GPT-4: 10.1 (#304), GPT-4.1 nano: 25.5 (#246)

BenchmarkGPT-4GPT-4.1 nano
OTIS Mock AIME 2024-20251.1%28.9%
LMArena Math12691274
MATH Level 523%70%
Omni-MATH—36.7%
FrontierMath (Feb 2025 set)—1%
GSM8K92%—

Knowledge GPT-4.1 nano leads

GPT-4: 18.4 (#277), GPT-4.1 nano: 21.8 (#268)

BenchmarkGPT-4GPT-4.1 nano
GPQA Diamond35.7%48.9%
LMArena Expert12111272
SimpleQA Verified—6%
MMLU-Pro—55%
GPQA (HELM)—50.7%
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, GPT-4.1 nano: 28.6 (#108)

BenchmarkGPT-4GPT-4.1 nano
LMArena Vision—1063

Multilingual GPT-4.1 nano leads

GPT-4: 40.8 (#210), GPT-4.1 nano: 41.8 (#200)

BenchmarkGPT-4GPT-4.1 nano
LMArena Non-English12461260
LMArena Chinese12421270
LMArena German12511288
LMArena Japanese12091199
LMArena Russian12511261
LMArena French1282—
LMArena Korean1184—
LMArena Spanish1261—

Instruction Following GPT-4.1 nano leads

GPT-4: 65.5 (#217), GPT-4.1 nano: 68.0 (#188)

BenchmarkGPT-4GPT-4.1 nano
LMArena Instruction Following12411267
IFEval—84.3%

Long Context GPT-4 leads

GPT-4: 37.7 (#207), GPT-4.1 nano: 23.7 (#291)

BenchmarkGPT-4GPT-4.1 nano
LMArena Longer Query12441283
Fiction.LiveBench—25%

Writing & Preference GPT-4.1 nano leads

GPT-4: 35.0 (#263), GPT-4.1 nano: 40.7 (#238)

BenchmarkGPT-4GPT-4.1 nano
LMArena Text12631285
LMArena Creative Writing12441260
EQ-Bench Creative Writing752946
LMArena Multi-Turn12571277
WildBench—81.2%

Frequently asked questions

Is GPT-4 better than GPT-4.1 nano?

GPT-4 is the stronger model overall, scoring 28.9 to 27.7 on the Noometry Index. GPT-4.1 nano costs 214× less per token, which makes it the better buy when GPT-4's lead doesn't matter for your workload.

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

GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GPT-4 lists at $30 and $60.

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

GPT-4 scores higher on coding benchmarks: 31.2 versus 23.8 in the Noometry coding category.

Which has the bigger context window?

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

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

22 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and GPT-4.1 nano has 38.

Related comparisons

Go deeper