Noometry

Model comparison

Amazon Nova Lite vs Phi-4 Mini

Amazon Nova Lite is the stronger model overall, scoring 31.9 to 30.9 on the Noometry Index.

Last verified . 1 shared benchmarks.

Amazon Nova Lite Amazon

31.9

Rank #265 Confirmed

Phi-4 Mini Microsoft

30.9

Rank #283 Reported

Summary

  • They share 1 benchmark with published results for both. Amazon Nova Lite scores higher in 2 categories and Phi-4 Mini in 1 category; 2 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Amazon Nova Lite leads 32.5 to 28.1.
  • The biggest single-benchmark swing is Vectara Hallucination Rate: 6.1% for Amazon Nova Lite and 23.5% for Phi-4 Mini.
  • Amazon Nova Lite is cheaper at $0.06 / $0.24 per million input/output tokens, against $0.075 / $0.30 for Phi-4 Mini.
  • Amazon Nova Lite accepts more context: 300K tokens versus 128K.
  • Phi-4 Mini has downloadable open weights; the other is API-only.

Side by side

Amazon Nova LitePhi-4 Mini
ProviderAmazonMicrosoft
Noometry Index31.930.9
Released2024-12-032024-12-11
WeightsProprietaryOpen
Context window300K128K
Max output10K4K
Input $ / M tokens$0.06$0.075
Output $ / M tokens$0.24$0.30
Results tracked343

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

Category by category

Coding Amazon Nova Lite leads

Amazon Nova Lite: 32.5 (#270), Phi-4 Mini: 28.1 (#317)

BenchmarkAmazon Nova LitePhi-4 Mini
SciCode—10.8%
LiveBench Coding27.5%—
LMArena Coding1239—
ALE-Bench236.25—

Reasoning Phi-4 Mini leads

Amazon Nova Lite: 19.3 (#260), Phi-4 Mini: 22.4 (#195)

BenchmarkAmazon Nova LitePhi-4 Mini
CritPt—0%
LiveBench Reasoning36.7%—
LMArena Hard Prompts1220—
LiveBench Data Analysis37.2%—
LiveBench36.4%—

Math Not comparable

Amazon Nova Lite: 27.8 (#247), Phi-4 Mini: —

BenchmarkAmazon Nova LitePhi-4 Mini
Omni-MATH23.3%—
LiveBench Math36.7%—
LMArena Math1227—

Knowledge Too close to call

Amazon Nova Lite: 26.3 (#259), Phi-4 Mini: 25.3 (#262)

BenchmarkAmazon Nova LitePhi-4 Mini
Vectara Hallucination Rate6.1%23.5%
Humanity's Last Exam3.6%—
MMLU-Pro60%—
GPQA (HELM)39.7%—
LMArena Expert1201—
MMLU77%—

Multimodal Not comparable

Amazon Nova Lite: 25.5 (#123), Phi-4 Mini: —

BenchmarkAmazon Nova LitePhi-4 Mini
LMArena Vision990—

Multilingual Not comparable

Amazon Nova Lite: 38.0 (#232), Phi-4 Mini: —

BenchmarkAmazon Nova LitePhi-4 Mini
LMArena Non-English1208—
LMArena Chinese1225—
LMArena French1237—
LMArena German1229—
LMArena Japanese1153—
LMArena Korean1153—
LMArena Russian1216—
LMArena Spanish1226—

Instruction Following Not comparable

Amazon Nova Lite: 59.3 (#255), Phi-4 Mini: —

BenchmarkAmazon Nova LitePhi-4 Mini
LiveBench Instruction Following54.1%—
IFEval77.6%—
LMArena Instruction Following1205—

Long Context Not comparable

Amazon Nova Lite: 37.4 (#217), Phi-4 Mini: —

BenchmarkAmazon Nova LitePhi-4 Mini
LMArena Longer Query1234—

Writing & Preference Not comparable

Amazon Nova Lite: 42.1 (#237), Phi-4 Mini: —

BenchmarkAmazon Nova LitePhi-4 Mini
LMArena Text1229—
LMArena Creative Writing1197—
WildBench75%—
LMArena Multi-Turn1199—
LiveBench Language25.9%—

Frequently asked questions

Is Amazon Nova Lite better than Phi-4 Mini?

Amazon Nova Lite is the stronger model overall, scoring 31.9 to 30.9 on the Noometry Index.

Which is cheaper, Amazon Nova Lite or Phi-4 Mini?

Amazon Nova Lite is cheaper. It lists at $0.06 per million input tokens and $0.24 per million output tokens; Phi-4 Mini lists at $0.075 and $0.30.

Is Amazon Nova Lite or Phi-4 Mini better for coding?

Amazon Nova Lite scores higher on coding benchmarks: 32.5 versus 28.1 in the Noometry coding category.

Which has the bigger context window?

Amazon Nova Lite does, with 300K tokens against 128K.

How many benchmarks do Amazon Nova Lite and Phi-4 Mini share?

1 benchmark has published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Phi-4 Mini has 3.

Related comparisons

Go deeper