Noometry

Model comparison

Phi 3 Mini 4k Instruct vs Qwen3-30B-A3B

Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 27.4 on the Noometry Index.

Last verified . 18 shared benchmarks.

Phi 3 Mini 4k Instruct Microsoft

27.4

Rank #324 Confirmed

Qwen3-30B-A3B Alibaba (Qwen)

38.5

Rank #174 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 1 category and Qwen3-30B-A3B in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen3-30B-A3B leads 55.9 to 27.7.
  • The biggest single-benchmark swing is Chess Puzzles: 0% for Phi 3 Mini 4k Instruct and 8% for Qwen3-30B-A3B.

Side by side

Phi 3 Mini 4k InstructQwen3-30B-A3B
ProviderMicrosoftAlibaba (Qwen)
Noometry Index27.438.5
Released2024-04-232025-04-28
WeightsOpenOpen
Context window—41K
Max output—16K
Input $ / M tokens—$0.12
Output $ / M tokens—$0.50
Results tracked3532

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

Category by category

Coding Qwen3-30B-A3B leads

Phi 3 Mini 4k Instruct: 26.1 (#319), Qwen3-30B-A3B: 37.0 (#188)

BenchmarkPhi 3 Mini 4k InstructQwen3-30B-A3B
LMArena Coding10931416
SciCode—33.3%
WeirdML—29.8%
LiveBench Coding15.5%—
HumanEval+59.1%—
MBPP+54.2%—

Agentic & Tool Use Not comparable

Phi 3 Mini 4k Instruct: —, Qwen3-30B-A3B: 29.5 (#75)

BenchmarkPhi 3 Mini 4k InstructQwen3-30B-A3B
Berkeley Function Calling Leaderboard—41.4%

Reasoning Qwen3-30B-A3B leads

Phi 3 Mini 4k Instruct: 13.6 (#326), Qwen3-30B-A3B: 21.6 (#193)

BenchmarkPhi 3 Mini 4k InstructQwen3-30B-A3B
Chess Puzzles0%8%
LMArena Hard Prompts10721398
Kagi LLM Benchmark—54.9%
CritPt—0.3%
LiveBench Reasoning26.8%—
DTBench—69.3%
LiveBench Data Analysis34.7%—
LMCA—22.4%
Adversarial NLI52.8%—
BIG-Bench Hard71.7%—
Epoch Capabilities Index—139.63
HellaSwag76.7%—
LiveBench22.4%—
WinoGrande70.8%—

Math Qwen3-30B-A3B leads

Phi 3 Mini 4k Instruct: 24.5 (#258), Qwen3-30B-A3B: 36.0 (#133)

BenchmarkPhi 3 Mini 4k InstructQwen3-30B-A3B
LMArena Math11111394
MathArena Final-Answer Competitions—47.8%
OTIS Mock AIME 2024-2025—70.3%
LiveBench Math15.7%—

Knowledge Qwen3-30B-A3B leads

Phi 3 Mini 4k Instruct: 27.9 (#241), Qwen3-30B-A3B: 41.7 (#96)

BenchmarkPhi 3 Mini 4k InstructQwen3-30B-A3B
LMArena Expert10451395
GPQA Diamond—70.1%
Confabulations—12.3%
ARC (AI2) Challenge84.9%—
MMLU68.8%—
OpenBookQA88%—
TriviaQA64%—

Multilingual Qwen3-30B-A3B leads

Phi 3 Mini 4k Instruct: 26.5 (#275), Qwen3-30B-A3B: 49.8 (#126)

BenchmarkPhi 3 Mini 4k InstructQwen3-30B-A3B
LMArena Non-English10211372
LMArena Chinese10211434
LMArena French10751419
LMArena German10441379
LMArena Japanese9351338
LMArena Korean9051333
LMArena Russian10221369
LMArena Spanish10841403

Instruction Following Qwen3-30B-A3B leads

Phi 3 Mini 4k Instruct: 48.0 (#298), Qwen3-30B-A3B: 72.2 (#137)

BenchmarkPhi 3 Mini 4k InstructQwen3-30B-A3B
LMArena Instruction Following10531364
LiveBench Instruction Following39.1%—

Long Context Too close to call

Phi 3 Mini 4k Instruct: 31.7 (#271), Qwen3-30B-A3B: 31.0 (#278)

BenchmarkPhi 3 Mini 4k InstructQwen3-30B-A3B
LMArena Longer Query10441379
Fiction.LiveBench—40.6%

Writing & Preference Qwen3-30B-A3B leads

Phi 3 Mini 4k Instruct: 27.7 (#295), Qwen3-30B-A3B: 55.9 (#138)

BenchmarkPhi 3 Mini 4k InstructQwen3-30B-A3B
LMArena Text10731384
LMArena Creative Writing10371318
LMArena Multi-Turn10181378
Short-Story Creative Writing—75.3%
LiveBench Language9.2%—

Frequently asked questions

Is Phi 3 Mini 4k Instruct better than Qwen3-30B-A3B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 27.4 on the Noometry Index.

Is Phi 3 Mini 4k Instruct or Qwen3-30B-A3B better for coding?

Qwen3-30B-A3B scores higher on coding benchmarks: 37.0 versus 26.1 in the Noometry coding category.

How many benchmarks do Phi 3 Mini 4k Instruct and Qwen3-30B-A3B share?

18 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper