Noometry

Model comparison

Phi 3 Mini 128k Instruct vs Qwen3-4B

Qwen3-4B is the stronger model overall, scoring 31.5 to 29.1 on the Noometry Index.

Last verified . 0 shared benchmarks.

Phi 3 Mini 128k Instruct Microsoft

29.1

Rank #303 Confirmed

Qwen3-4B Alibaba (Qwen)

31.5

Rank #261 Confirmed

Summary

  • The widest gap is in knowledge, where Qwen3-4B leads 33.0 to 26.3.

Side by side

Phi 3 Mini 128k InstructQwen3-4B
ProviderMicrosoftAlibaba (Qwen)
Noometry Index29.131.5
Released2024-04-232025-04-29
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked196

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

Category by category

Coding Not comparable

Phi 3 Mini 128k Instruct: 28.3 (#307), Qwen3-4B: —

BenchmarkPhi 3 Mini 128k InstructQwen3-4B
BigCodeBench Instruct29.6%—
LMArena Coding1040—
BigCodeBench Complete40.6%—

Agentic & Tool Use Not comparable

Phi 3 Mini 128k Instruct: —, Qwen3-4B: 27.3 (#94)

BenchmarkPhi 3 Mini 128k InstructQwen3-4B
Berkeley Function Calling Leaderboard—35.7%

Reasoning Too close to call

Phi 3 Mini 128k Instruct: 18.7 (#254), Qwen3-4B: 18.5 (#264)

BenchmarkPhi 3 Mini 128k InstructQwen3-4B
Chess Puzzles—4%
LMArena Hard Prompts1028—

Math Too close to call

Phi 3 Mini 128k Instruct: 29.2 (#220), Qwen3-4B: 28.5 (#228)

BenchmarkPhi 3 Mini 128k InstructQwen3-4B
MathArena Final-Answer Competitions—38.5%
OTIS Mock AIME 2024-2025—52.2%
LMArena Math1089—

Knowledge Qwen3-4B leads

Phi 3 Mini 128k Instruct: 26.3 (#251), Qwen3-4B: 33.0 (#198)

BenchmarkPhi 3 Mini 128k InstructQwen3-4B
GPQA Diamond—52.3%
Vectara Hallucination Rate—5.7%
LMArena Expert984—

Multilingual Not comparable

Phi 3 Mini 128k Instruct: 25.4 (#280), Qwen3-4B: —

BenchmarkPhi 3 Mini 128k InstructQwen3-4B
LMArena Non-English1000—
LMArena Chinese1016—
LMArena French1038—
LMArena German1006—
LMArena Japanese899—
LMArena Korean856—
LMArena Russian1004—
LMArena Spanish1058—

Instruction Following Not comparable

Phi 3 Mini 128k Instruct: 52.1 (#289), Qwen3-4B: —

BenchmarkPhi 3 Mini 128k InstructQwen3-4B
LMArena Instruction Following1023—

Long Context Not comparable

Phi 3 Mini 128k Instruct: 30.3 (#284), Qwen3-4B: —

BenchmarkPhi 3 Mini 128k InstructQwen3-4B
LMArena Longer Query996—

Writing & Preference Not comparable

Phi 3 Mini 128k Instruct: 27.3 (#296), Qwen3-4B: —

BenchmarkPhi 3 Mini 128k InstructQwen3-4B
LMArena Text1050—
LMArena Creative Writing1024—
LMArena Multi-Turn989—

Frequently asked questions

Is Phi 3 Mini 128k Instruct better than Qwen3-4B?

Qwen3-4B is the stronger model overall, scoring 31.5 to 29.1 on the Noometry Index.

How many benchmarks do Phi 3 Mini 128k Instruct and Qwen3-4B share?

0 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper