Model comparison

Amazon Nova Micro vs Phi 3 Medium 4k Instruct

Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 30.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

Amazon Nova Micro Amazon

30.4

Rank #294 Confirmed

Phi 3 Medium 4k Instruct Microsoft

33.0

Rank #250 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Amazon Nova Micro scores higher in 3 categories and Phi 3 Medium 4k Instruct in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Phi 3 Medium 4k Instruct leads 33.4 to 26.9.
  • Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.

Side by side

Amazon Nova Micro and Phi 3 Medium 4k Instruct specifications
Amazon Nova MicroPhi 3 Medium 4k Instruct
ProviderAmazonMicrosoft
Noometry Index30.433.0
Released2024-12-03—
WeightsProprietaryOpen
Context window128K—
Max output10K—
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked3217

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

Category by category

Coding Phi 3 Medium 4k Instruct leads

Amazon Nova Micro: 30.5 (#295), Phi 3 Medium 4k Instruct: 32.9 (#268)

Coding benchmarks
BenchmarkAmazon Nova MicroPhi 3 Medium 4k Instruct
LMArena Coding12181130
LiveBench Coding20.2%—

Agentic & Tool Use Not comparable

Amazon Nova Micro: 22.1 (#132), Phi 3 Medium 4k Instruct: —

Agentic & Tool Use benchmarks
BenchmarkAmazon Nova MicroPhi 3 Medium 4k Instruct
Berkeley Function Calling Leaderboard22.3%—

Reasoning Phi 3 Medium 4k Instruct leads

Amazon Nova Micro: 17.4 (#294), Phi 3 Medium 4k Instruct: 21.7 (#214)

Reasoning benchmarks
BenchmarkAmazon Nova MicroPhi 3 Medium 4k Instruct
LMArena Hard Prompts11911127
LiveBench Reasoning25.1%—
LiveBench Data Analysis34%—
LiveBench29.6%—

Math Phi 3 Medium 4k Instruct leads

Amazon Nova Micro: 26.9 (#254), Phi 3 Medium 4k Instruct: 33.4 (#202)

Math benchmarks
BenchmarkAmazon Nova MicroPhi 3 Medium 4k Instruct
LMArena Math12061173
Omni-MATH21.4%—
LiveBench Math34.5%—

Knowledge Too close to call

Amazon Nova Micro: 29.6 (#237), Phi 3 Medium 4k Instruct: 30.2 (#229)

Knowledge benchmarks
BenchmarkAmazon Nova MicroPhi 3 Medium 4k Instruct
LMArena Expert11841108
MMLU-Pro51.1%—
Vectara Hallucination Rate5.5%—
GPQA (HELM)38.3%—
MMLU70.8%—

Multilingual Amazon Nova Micro leads

Amazon Nova Micro: 36.5 (#239), Phi 3 Medium 4k Instruct: 30.6 (#263)

Multilingual benchmarks
BenchmarkAmazon Nova MicroPhi 3 Medium 4k Instruct
LMArena Non-English11861094
LMArena Chinese12091108
LMArena French12381110
LMArena German11921101
LMArena Japanese11541042
LMArena Korean1150954
LMArena Russian11851145
LMArena Spanish12251095

Instruction Following Phi 3 Medium 4k Instruct leads

Amazon Nova Micro: 56.3 (#272), Phi 3 Medium 4k Instruct: 57.6 (#268)

Instruction Following benchmarks
BenchmarkAmazon Nova MicroPhi 3 Medium 4k Instruct
LMArena Instruction Following11741113
LiveBench Instruction Following48%—
IFEval76%—

Long Context Amazon Nova Micro leads

Amazon Nova Micro: 36.5 (#229), Phi 3 Medium 4k Instruct: 34.0 (#255)

Long Context benchmarks
BenchmarkAmazon Nova MicroPhi 3 Medium 4k Instruct
LMArena Longer Query12051120

Writing & Preference Amazon Nova Micro leads

Amazon Nova Micro: 39.5 (#247), Phi 3 Medium 4k Instruct: 34.1 (#272)

Writing & Preference benchmarks
BenchmarkAmazon Nova MicroPhi 3 Medium 4k Instruct
LMArena Text12081138
LMArena Creative Writing11721107
LMArena Multi-Turn11781088
WildBench74.3%—
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than Phi 3 Medium 4k Instruct?

Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 30.4 on the Noometry Index.

Is Amazon Nova Micro or Phi 3 Medium 4k Instruct better for coding?

Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.9 versus 30.5 in the Noometry coding category.

How many benchmarks do Amazon Nova Micro and Phi 3 Medium 4k Instruct share?

17 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.

Related comparisons

Go deeper