Noometry

Model comparison

GPT-4.1 nano vs Phi-4

Phi-4 is the stronger model overall, scoring 31.2 to 27.9 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-4.1 nano OpenAI

27.9

Rank #327 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4.1 nano scores higher in 5 categories and Phi-4 in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Phi-4 leads 36.9 to 23.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 28.9% for GPT-4.1 nano and 13.8% for Phi-4.
  • Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.10 / $0.40 for GPT-4.1 nano.
  • GPT-4.1 nano accepts more context: 1.05M tokens versus 128K.
  • Phi-4 has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 nanoPhi-4
ProviderOpenAIMicrosoft
Noometry Index27.931.2
Released2025-04-142024-12-11
WeightsProprietaryOpen
Context window1.05M128K
Max output33K4K
Input $ / M tokens$0.10$0.07
Output $ / M tokens$0.40$0.14
Results tracked3837

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

Category by category

Coding Phi-4 leads

GPT-4.1 nano: 24.1 (#330), Phi-4: 34.4 (#239)

BenchmarkGPT-4.1 nanoPhi-4
LMArena Coding13061231
Aider Polyglot8.9%—
SciCode25.9%—
WeirdML19%—
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%

Agentic & Tool Use GPT-4.1 nano leads

GPT-4.1 nano: 26.5 (#104), Phi-4: 22.8 (#128)

BenchmarkGPT-4.1 nanoPhi-4
Berkeley Function Calling Leaderboard33%28.8%
BALROG—11.6%

Reasoning Phi-4 leads

GPT-4.1 nano: 8.5 (#349), Phi-4: 17.7 (#291)

BenchmarkGPT-4.1 nanoPhi-4
LMArena Hard Prompts12861220
Epoch Capabilities Index129.62130.42
ARC-AGI-20%—
Kagi LLM Benchmark33.3%—
ARC-AGI-10%—
CritPt0%—
Chess Puzzles—1%
LiveBench Reasoning—47.8%
DTBench52.5%—
LiveBench Data Analysis—45.2%
LMCA5.5%—
LiveBench—41.6%

Math GPT-4.1 nano leads

GPT-4.1 nano: 26.9 (#252), Phi-4: 20.8 (#285)

BenchmarkGPT-4.1 nanoPhi-4
OTIS Mock AIME 2024-202528.9%13.8%
LMArena Math12741246
MATH Level 570%64.9%
Omni-MATH36.7%—
LiveBench Math—42%
FrontierMath (Feb 2025 set)1%—

Knowledge Phi-4 leads

GPT-4.1 nano: 21.8 (#273), Phi-4: 32.6 (#209)

BenchmarkGPT-4.1 nanoPhi-4
GPQA Diamond48.9%56.1%
LMArena Expert12721203
SimpleQA Verified6%—
MMLU-Pro55%—
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
GPQA (HELM)50.7%—
MMLU—84.8%

Multimodal Not comparable

GPT-4.1 nano: 29.2 (#113), Phi-4: —

BenchmarkGPT-4.1 nanoPhi-4
LMArena Vision1063—

Multilingual GPT-4.1 nano leads

GPT-4.1 nano: 41.6 (#205), Phi-4: 37.2 (#237)

BenchmarkGPT-4.1 nanoPhi-4
LMArena Non-English12601197
LMArena Chinese12701212
LMArena German12881222
LMArena Japanese11981158
LMArena Russian12611209
LMArena French—1224
LMArena Korean—1151
LMArena Spanish—1234

Instruction Following GPT-4.1 nano leads

GPT-4.1 nano: 67.8 (#193), Phi-4: 60.4 (#251)

BenchmarkGPT-4.1 nanoPhi-4
LMArena Instruction Following12671201
LiveBench Instruction Following—58.4%
IFEval84.3%—

Long Context Phi-4 leads

GPT-4.1 nano: 23.7 (#296), Phi-4: 36.9 (#226)

BenchmarkGPT-4.1 nanoPhi-4
LMArena Longer Query12831217
Fiction.LiveBench25%—

Writing & Preference Too close to call

GPT-4.1 nano: 40.5 (#243), Phi-4: 40.5 (#244)

BenchmarkGPT-4.1 nanoPhi-4
LMArena Text12851217
LMArena Creative Writing12601182
LMArena Multi-Turn12771206
Short-Story Creative Writing—62.6%
EQ-Bench Creative Writing946—
WildBench81.2%—
LiveBench Language—25.6%

Frequently asked questions

Is GPT-4.1 nano better than Phi-4?

Phi-4 is the stronger model overall, scoring 31.2 to 27.9 on the Noometry Index.

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

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; GPT-4.1 nano lists at $0.10 and $0.40.

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

Phi-4 scores higher on coding benchmarks: 34.4 versus 24.1 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 nano does, with 1.05M tokens against 128K.

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

19 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper