Noometry

Model comparison

GPT-4.1 mini vs phi-3-medium 14B

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 29.7 on the Noometry Index.

Last verified . 4 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

phi-3-medium 14B Microsoft

29.7

Rank #306 Reported

Summary

  • They share 4 benchmarks with published results for both. GPT-4.1 mini scores higher in 1 category and phi-3-medium 14B in 2 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.1 mini leads 34.7 to 9.1.
  • The biggest single-benchmark swing is MATH Level 5: 87.3% for GPT-4.1 mini and 17.6% for phi-3-medium 14B.
  • phi-3-medium 14B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniphi-3-medium 14B
ProviderOpenAIMicrosoft
Noometry Index33.629.7
Released2025-04-142024-04-23
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4713

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

Category by category

Coding phi-3-medium 14B leads

GPT-4.1 mini: 30.6 (#293), phi-3-medium 14B: 36.8 (#201)

BenchmarkGPT-4.1 miniphi-3-medium 14B
BigCodeBench Instruct48.9%37.6%
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
SciCode40.4%—
WeirdML37.6%—
LMArena Coding1367—
BigCodeBench Complete—48.7%
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.3 (#55), phi-3-medium 14B: —

BenchmarkGPT-4.1 miniphi-3-medium 14B
Berkeley Function Calling Leaderboard50.5%—

Reasoning Not comparable

GPT-4.1 mini: 10.8 (#340), phi-3-medium 14B: —

BenchmarkGPT-4.1 miniphi-3-medium 14B
Epoch Capabilities Index135.01121.23
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
LMArena Hard Prompts1349—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—
Adversarial NLI—55.8%
BIG-Bench Hard—81.4%
HellaSwag—82.4%
WinoGrande—81.5%

Math phi-3-medium 14B leads

GPT-4.1 mini: 24.1 (#270), phi-3-medium 14B: 27.3 (#250)

BenchmarkGPT-4.1 miniphi-3-medium 14B
MATH Level 587.3%17.6%
FrontierMath (Tiers 1-3)6.7%—
OTIS Mock AIME 2024-202544.7%—
Omni-MATH49.1%—
LMArena Math1343—
FrontierMath (Feb 2025 set)4.5%—

Knowledge GPT-4.1 mini leads

GPT-4.1 mini: 34.7 (#194), phi-3-medium 14B: 9.1 (#306)

BenchmarkGPT-4.1 miniphi-3-medium 14B
GPQA Diamond65.8%27.6%
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—
LMArena Expert1338—
ARC (AI2) Challenge—91.6%
MMLU—78%
OpenBookQA—87.4%
TriviaQA—73.9%

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), phi-3-medium 14B: —

BenchmarkGPT-4.1 miniphi-3-medium 14B
LMArena Vision1181—

Multilingual Not comparable

GPT-4.1 mini: 45.7 (#166), phi-3-medium 14B: —

BenchmarkGPT-4.1 miniphi-3-medium 14B
LMArena Non-English1318—
LMArena Chinese1329—
LMArena French1358—
LMArena German1351—
LMArena Japanese1290—
LMArena Korean1298—
LMArena Russian1324—
LMArena Spanish1319—

Instruction Following Not comparable

GPT-4.1 mini: 73.7 (#118), phi-3-medium 14B: —

BenchmarkGPT-4.1 miniphi-3-medium 14B
IFEval90.4%—
LMArena Instruction Following1333—

Long Context Not comparable

GPT-4.1 mini: 31.8 (#275), phi-3-medium 14B: —

BenchmarkGPT-4.1 miniphi-3-medium 14B
Fiction.LiveBench44.4%—
LMArena Longer Query1344—

Writing & Preference Not comparable

GPT-4.1 mini: 48.6 (#199), phi-3-medium 14B: —

BenchmarkGPT-4.1 miniphi-3-medium 14B
LMArena Text1340—
LMArena Creative Writing1300—
EQ-Bench Creative Writing1147—
WildBench83.8%—
LMArena Multi-Turn1354—

Frequently asked questions

Is GPT-4.1 mini better than phi-3-medium 14B?

GPT-4.1 mini is the stronger model overall, scoring 33.6 to 29.7 on the Noometry Index.

Is GPT-4.1 mini or phi-3-medium 14B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 30.6 in the Noometry coding category.

How many benchmarks do GPT-4.1 mini and phi-3-medium 14B share?

4 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and phi-3-medium 14B has 13.

Related comparisons

Go deeper