Model comparison

Nova Premier 1.0 vs Phi 3 Medium 4k Instruct

Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 33.0 on the Noometry Index.

Last verified . 0 shared benchmarks.

Nova Premier 1.0 Amazon

38.3

Rank #189 Confirmed

Phi 3 Medium 4k Instruct Microsoft

33.0

Rank #250 Confirmed

Summary

  • The widest gap is in writing & preference, where Nova Premier 1.0 leads 51.0 to 34.1.
  • Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.

Side by side

Nova Premier 1.0 and Phi 3 Medium 4k Instruct specifications
Nova Premier 1.0Phi 3 Medium 4k Instruct
ProviderAmazonMicrosoft
Noometry Index38.333.0
Released2025-04-30—
WeightsProprietaryOpen
Context window1M—
Max output10K—
Input $ / M tokens$2.50—
Output $ / M tokens$12.50—
Results tracked617

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

Category by category

Coding Not comparable

Nova Premier 1.0: —, Phi 3 Medium 4k Instruct: 32.9 (#268)

Coding benchmarks
BenchmarkNova Premier 1.0Phi 3 Medium 4k Instruct
LMArena Coding—1130

Reasoning Nova Premier 1.0 leads

Nova Premier 1.0: 23.0 (#185), Phi 3 Medium 4k Instruct: 21.7 (#214)

Reasoning benchmarks
BenchmarkNova Premier 1.0Phi 3 Medium 4k Instruct
Kagi LLM Benchmark44.8%—
LMArena Hard Prompts—1127

Math Too close to call

Nova Premier 1.0: 33.8 (#199), Phi 3 Medium 4k Instruct: 33.4 (#202)

Math benchmarks
BenchmarkNova Premier 1.0Phi 3 Medium 4k Instruct
Omni-MATH35%—
LMArena Math—1173

Knowledge Nova Premier 1.0 leads

Nova Premier 1.0: 35.8 (#180), Phi 3 Medium 4k Instruct: 30.2 (#229)

Knowledge benchmarks
BenchmarkNova Premier 1.0Phi 3 Medium 4k Instruct
MMLU-Pro72.6%—
GPQA (HELM)51.8%—
LMArena Expert—1108

Multilingual Not comparable

Nova Premier 1.0: —, Phi 3 Medium 4k Instruct: 30.6 (#263)

Multilingual benchmarks
BenchmarkNova Premier 1.0Phi 3 Medium 4k Instruct
LMArena Non-English—1094
LMArena Chinese—1108
LMArena French—1110
LMArena German—1101
LMArena Japanese—1042
LMArena Korean—954
LMArena Russian—1145
LMArena Spanish—1095

Instruction Following Nova Premier 1.0 leads

Nova Premier 1.0: 66.8 (#204), Phi 3 Medium 4k Instruct: 57.6 (#268)

Instruction Following benchmarks
BenchmarkNova Premier 1.0Phi 3 Medium 4k Instruct
IFEval80.3%—
LMArena Instruction Following—1113

Long Context Not comparable

Nova Premier 1.0: —, Phi 3 Medium 4k Instruct: 34.0 (#255)

Long Context benchmarks
BenchmarkNova Premier 1.0Phi 3 Medium 4k Instruct
LMArena Longer Query—1120

Writing & Preference Nova Premier 1.0 leads

Nova Premier 1.0: 51.0 (#178), Phi 3 Medium 4k Instruct: 34.1 (#272)

Writing & Preference benchmarks
BenchmarkNova Premier 1.0Phi 3 Medium 4k Instruct
LMArena Text—1138
LMArena Creative Writing—1107
WildBench78.8%—
LMArena Multi-Turn—1088

Frequently asked questions

Is Nova Premier 1.0 better than Phi 3 Medium 4k Instruct?

Nova Premier 1.0 is the stronger model overall, scoring 38.3 to 33.0 on the Noometry Index.

How many benchmarks do Nova Premier 1.0 and Phi 3 Medium 4k Instruct share?

0 benchmarks have published results for both models. Nova Premier 1.0 has 6 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.

Related comparisons

Go deeper