Noometry

Model comparison

Phi 3 Mini 4k Instruct vs Phi-4

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

Last verified . 26 shared benchmarks.

Phi 3 Mini 4k Instruct Microsoft

27.9

Rank #328 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 26 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 1 category and Phi-4 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Phi-4 leads 40.5 to 27.6.
  • The biggest single-benchmark swing is LiveBench Math: 15.7% for Phi 3 Mini 4k Instruct and 42% for Phi-4.

Side by side

Phi 3 Mini 4k InstructPhi-4
ProviderMicrosoftMicrosoft
Noometry Index27.931.2
Released2024-04-232024-12-11
WeightsOpenOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.07
Output $ / M tokens—$0.14
Results tracked3537

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

Category by category

Coding Phi-4 leads

Phi 3 Mini 4k Instruct: 26.6 (#323), Phi-4: 34.4 (#239)

BenchmarkPhi 3 Mini 4k InstructPhi-4
LiveBench Coding15.5%30.7%
LMArena Coding10931231
BigCodeBench Instruct—45.5%
BigCodeBench Complete—55.4%
HumanEval+59.1%—
MBPP+54.2%—

Agentic & Tool Use Not comparable

Phi 3 Mini 4k Instruct: —, Phi-4: 22.8 (#128)

BenchmarkPhi 3 Mini 4k InstructPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning Phi-4 leads

Phi 3 Mini 4k Instruct: 14.1 (#328), Phi-4: 17.7 (#291)

BenchmarkPhi 3 Mini 4k InstructPhi-4
Chess Puzzles0%1%
LiveBench Reasoning26.8%47.8%
LMArena Hard Prompts10721220
LiveBench Data Analysis34.7%45.2%
LiveBench22.4%41.6%
Adversarial NLI52.8%—
BIG-Bench Hard71.7%—
Epoch Capabilities Index—130.42
HellaSwag76.7%—
WinoGrande70.8%—

Math Phi 3 Mini 4k Instruct leads

Phi 3 Mini 4k Instruct: 26.6 (#257), Phi-4: 20.8 (#285)

BenchmarkPhi 3 Mini 4k InstructPhi-4
LiveBench Math15.7%42%
LMArena Math11111246
OTIS Mock AIME 2024-2025—13.8%
MATH Level 5—64.9%

Knowledge Phi-4 leads

Phi 3 Mini 4k Instruct: 28.5 (#246), Phi-4: 32.6 (#209)

BenchmarkPhi 3 Mini 4k InstructPhi-4
LMArena Expert10451203
MMLU68.8%84.8%
GPQA Diamond—56.1%
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
ARC (AI2) Challenge84.9%—
OpenBookQA88%—
TriviaQA64%—

Multilingual Phi-4 leads

Phi 3 Mini 4k Instruct: 26.3 (#280), Phi-4: 37.2 (#237)

BenchmarkPhi 3 Mini 4k InstructPhi-4
LMArena Non-English10211197
LMArena Chinese10211212
LMArena French10761224
LMArena German10441222
LMArena Japanese9351158
LMArena Korean9051151
LMArena Russian10221209
LMArena Spanish10851234

Instruction Following Phi-4 leads

Phi 3 Mini 4k Instruct: 47.7 (#303), Phi-4: 60.4 (#251)

BenchmarkPhi 3 Mini 4k InstructPhi-4
LiveBench Instruction Following39.1%58.4%
LMArena Instruction Following10531201

Long Context Phi-4 leads

Phi 3 Mini 4k Instruct: 31.7 (#276), Phi-4: 36.9 (#226)

BenchmarkPhi 3 Mini 4k InstructPhi-4
LMArena Longer Query10441217

Writing & Preference Phi-4 leads

Phi 3 Mini 4k Instruct: 27.6 (#300), Phi-4: 40.5 (#244)

BenchmarkPhi 3 Mini 4k InstructPhi-4
LMArena Text10731217
LMArena Creative Writing10371182
LMArena Multi-Turn10181206
LiveBench Language9.2%25.6%
Short-Story Creative Writing—62.6%

Frequently asked questions

Is Phi 3 Mini 4k Instruct better than Phi-4?

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

Is Phi 3 Mini 4k Instruct or Phi-4 better for coding?

Phi-4 scores higher on coding benchmarks: 34.4 versus 26.6 in the Noometry coding category.

How many benchmarks do Phi 3 Mini 4k Instruct and Phi-4 share?

26 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper