Noometry

Model comparison

Phi 3 Mini 4k Instruct vs Qwen3.5-Flash

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 27.9 on the Noometry Index.

Last verified . 18 shared benchmarks.

Phi 3 Mini 4k Instruct Microsoft

27.9

Rank #328 Confirmed

Qwen3.5-Flash Alibaba (Qwen)

42.5

Rank #112 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Qwen3.5-Flash in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen3.5-Flash leads 57.9 to 27.6.
  • The biggest single-benchmark swing is Chess Puzzles: 0% for Phi 3 Mini 4k Instruct and 21% for Qwen3.5-Flash.
  • Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.

Side by side

Phi 3 Mini 4k InstructQwen3.5-Flash
ProviderMicrosoftAlibaba (Qwen)
Noometry Index27.942.5
Released2024-04-232026-02-23
WeightsOpenProprietary
Context window—1M
Max output—66K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.40
Results tracked3532

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

Category by category

Coding Qwen3.5-Flash leads

Phi 3 Mini 4k Instruct: 26.6 (#323), Qwen3.5-Flash: 34.2 (#242)

BenchmarkPhi 3 Mini 4k InstructQwen3.5-Flash
LMArena Coding10931412
LMArena WebDev—1244
LiveBench Coding15.5%—
ALE-Bench—221.8
HumanEval+59.1%—
MBPP+54.2%—

Agentic & Tool Use Not comparable

Phi 3 Mini 4k Instruct: —, Qwen3.5-Flash: —

BenchmarkPhi 3 Mini 4k InstructQwen3.5-Flash
Vending-Bench 2—462.69

Reasoning Qwen3.5-Flash leads

Phi 3 Mini 4k Instruct: 14.1 (#328), Qwen3.5-Flash: 33.7 (#72)

BenchmarkPhi 3 Mini 4k InstructQwen3.5-Flash
Chess Puzzles0%21%
LMArena Hard Prompts10721403
LiveBench Reasoning26.8%—
Mystery Game Puzzles—20%
DTBench—82.9%
LiveBench Data Analysis34.7%—
LMCA—29.1%
Adversarial NLI52.8%—
BIG-Bench Hard71.7%—
Epoch Capabilities Index—143.98
HellaSwag76.7%—
LiveBench22.4%—
WinoGrande70.8%—

Math Qwen3.5-Flash leads

Phi 3 Mini 4k Instruct: 26.6 (#257), Qwen3.5-Flash: 37.4 (#158)

BenchmarkPhi 3 Mini 4k InstructQwen3.5-Flash
LMArena Math11111407
FrontierMath (Tiers 1-3)—18.2%
OTIS Mock AIME 2024-2025—84.4%
LiveBench Math15.7%—
FrontierMath (Feb 2025 set)—6.2%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3.5-Flash leads

Phi 3 Mini 4k Instruct: 28.5 (#246), Qwen3.5-Flash: 43.2 (#93)

BenchmarkPhi 3 Mini 4k InstructQwen3.5-Flash
LMArena Expert10451407
GPQA Diamond—82.3%
SimpleQA Verified—20.3%
Vectara Hallucination Rate—10.5%
ARC (AI2) Challenge84.9%—
MMLU68.8%—
OpenBookQA88%—
TriviaQA64%—

Multilingual Qwen3.5-Flash leads

Phi 3 Mini 4k Instruct: 26.3 (#280), Qwen3.5-Flash: 50.5 (#121)

BenchmarkPhi 3 Mini 4k InstructQwen3.5-Flash
LMArena Non-English10211385
LMArena Chinese10211446
LMArena French10761412
LMArena German10441390
LMArena Japanese9351368
LMArena Korean9051344
LMArena Russian10221379
LMArena Spanish10851400

Instruction Following Qwen3.5-Flash leads

Phi 3 Mini 4k Instruct: 47.7 (#303), Qwen3.5-Flash: 72.6 (#139)

BenchmarkPhi 3 Mini 4k InstructQwen3.5-Flash
LMArena Instruction Following10531374
LiveBench Instruction Following39.1%—

Long Context Qwen3.5-Flash leads

Phi 3 Mini 4k Instruct: 31.7 (#276), Qwen3.5-Flash: 42.4 (#124)

BenchmarkPhi 3 Mini 4k InstructQwen3.5-Flash
LMArena Longer Query10441392

Writing & Preference Qwen3.5-Flash leads

Phi 3 Mini 4k Instruct: 27.6 (#300), Qwen3.5-Flash: 57.9 (#122)

BenchmarkPhi 3 Mini 4k InstructQwen3.5-Flash
LMArena Text10731397
LMArena Creative Writing10371343
LMArena Multi-Turn10181393
LiveBench Language9.2%—

Frequently asked questions

Is Phi 3 Mini 4k Instruct better than Qwen3.5-Flash?

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 27.9 on the Noometry Index.

Is Phi 3 Mini 4k Instruct or Qwen3.5-Flash better for coding?

Qwen3.5-Flash scores higher on coding benchmarks: 34.2 versus 26.6 in the Noometry coding category.

How many benchmarks do Phi 3 Mini 4k Instruct and Qwen3.5-Flash share?

18 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen3.5-Flash has 32.

Related comparisons

Go deeper