Noometry

Model comparison

Phi 3 Mini 4k Instruct vs Qwen3 32B

Qwen3 32B is the stronger model overall, scoring 39.2 to 27.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

Phi 3 Mini 4k Instruct Microsoft

27.9

Rank #328 Confirmed

Qwen3 32B Alibaba (Qwen)

39.2

Rank #172 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Qwen3 32B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen3 32B leads 52.9 to 27.6.
  • The biggest single-benchmark swing is Chess Puzzles: 0% for Phi 3 Mini 4k Instruct and 5% for Qwen3 32B.

Side by side

Phi 3 Mini 4k InstructQwen3 32B
ProviderMicrosoftAlibaba (Qwen)
Noometry Index27.939.2
Released2024-04-232025-04
WeightsOpenOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked3526

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

Category by category

Coding Qwen3 32B leads

Phi 3 Mini 4k Instruct: 26.6 (#323), Qwen3 32B: 37.7 (#190)

BenchmarkPhi 3 Mini 4k InstructQwen3 32B
LMArena Coding10931358
Aider Polyglot—40%
SciCode—35.4%
LiveBench Coding15.5%—
HumanEval+59.1%—
MBPP+54.2%—

Agentic & Tool Use Not comparable

Phi 3 Mini 4k Instruct: —, Qwen3 32B: 32.6 (#62)

BenchmarkPhi 3 Mini 4k InstructQwen3 32B
Berkeley Function Calling Leaderboard—48.7%

Reasoning Qwen3 32B leads

Phi 3 Mini 4k Instruct: 14.1 (#328), Qwen3 32B: 20.2 (#241)

BenchmarkPhi 3 Mini 4k InstructQwen3 32B
Chess Puzzles0%5%
LMArena Hard Prompts10721334
Kagi LLM Benchmark—54.9%
CritPt—0.3%
LiveBench Reasoning26.8%—
DTBench—67.5%
LiveBench Data Analysis34.7%—
LMCA—17.3%
Adversarial NLI52.8%—
BIG-Bench Hard71.7%—
Epoch Capabilities Index—138.51
HellaSwag76.7%—
LiveBench22.4%—
WinoGrande70.8%—

Math Qwen3 32B leads

Phi 3 Mini 4k Instruct: 26.6 (#257), Qwen3 32B: 39.7 (#99)

BenchmarkPhi 3 Mini 4k InstructQwen3 32B
LMArena Math11111399
OTIS Mock AIME 2024-2025—66.9%
LiveBench Math15.7%—

Knowledge Qwen3 32B leads

Phi 3 Mini 4k Instruct: 28.5 (#246), Qwen3 32B: 40.0 (#125)

BenchmarkPhi 3 Mini 4k InstructQwen3 32B
LMArena Expert10451362
GPQA Diamond—65.7%
Vectara Hallucination Rate—5.9%
ARC (AI2) Challenge84.9%—
MMLU68.8%—
OpenBookQA88%—
TriviaQA64%—

Multilingual Qwen3 32B leads

Phi 3 Mini 4k Instruct: 26.3 (#280), Qwen3 32B: 45.6 (#167)

BenchmarkPhi 3 Mini 4k InstructQwen3 32B
LMArena Non-English10211317
LMArena Chinese10211357
LMArena German10441341
LMArena Russian10221311
LMArena French1076—
LMArena Japanese935—
LMArena Korean905—
LMArena Spanish1085—

Instruction Following Qwen3 32B leads

Phi 3 Mini 4k Instruct: 47.7 (#303), Qwen3 32B: 68.9 (#179)

BenchmarkPhi 3 Mini 4k InstructQwen3 32B
LMArena Instruction Following10531305
LiveBench Instruction Following39.1%—

Long Context Qwen3 32B leads

Phi 3 Mini 4k Instruct: 31.7 (#276), Qwen3 32B: 43.8 (#87)

BenchmarkPhi 3 Mini 4k InstructQwen3 32B
LMArena Longer Query10441327
Fiction.LiveBench—74.2%

Writing & Preference Qwen3 32B leads

Phi 3 Mini 4k Instruct: 27.6 (#300), Qwen3 32B: 52.9 (#163)

BenchmarkPhi 3 Mini 4k InstructQwen3 32B
LMArena Text10731340
LMArena Creative Writing10371297
LMArena Multi-Turn10181331
LiveBench Language9.2%—

Frequently asked questions

Is Phi 3 Mini 4k Instruct better than Qwen3 32B?

Qwen3 32B is the stronger model overall, scoring 39.2 to 27.9 on the Noometry Index.

Is Phi 3 Mini 4k Instruct or Qwen3 32B better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.7 versus 26.6 in the Noometry coding category.

How many benchmarks do Phi 3 Mini 4k Instruct and Qwen3 32B share?

14 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper