Noometry

Model comparison

Phi 3 Mini 4k Instruct vs Qwen3.8 27B

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 27.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Phi 3 Mini 4k Instruct Microsoft

27.9

Rank #328 Confirmed

Qwen3.8 27B Alibaba (Qwen)

46.0

Rank #68 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen3.8 27B leads 65.8 to 27.6.

Side by side

Phi 3 Mini 4k InstructQwen3.8 27B
ProviderMicrosoftAlibaba (Qwen)
Noometry Index27.946.0
Released2024-04-232026-08-14
WeightsOpenOpen
Context window—262K
Max output—33K
Input $ / M tokens—$0.04
Output $ / M tokens—$2.30
Results tracked3531

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

Category by category

Coding Qwen3.8 27B leads

Phi 3 Mini 4k Instruct: 26.6 (#323), Qwen3.8 27B: 50.5 (#44)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
LMArena Coding10931482
LMArena WebDev—1593
SciCode—46.6%
LiveBench Coding15.5%—
HumanEval+59.1%—
MBPP+54.2%—

Agentic & Tool Use Not comparable

Phi 3 Mini 4k Instruct: —, Qwen3.8 27B: 32.9 (#57)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
APEX-Agents—47.5%

Reasoning Qwen3.8 27B leads

Phi 3 Mini 4k Instruct: 14.1 (#328), Qwen3.8 27B: 41.0 (#54)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
LMArena Hard Prompts10721460
ARC-AGI-2—42.4%
NYT Connections (extended)—54.5%
ARC-AGI-1—87.5%
CritPt—5.4%
Chess Puzzles0%—
LiveBench Reasoning26.8%—
DTBench—88%
LiveBench Data Analysis34.7%—
LMCA—41.4%
Surface Evolver Bench—45%
Adversarial NLI52.8%—
BIG-Bench Hard71.7%—
Epoch Capabilities Index—149.38
HellaSwag76.7%—
LiveBench22.4%—
WinoGrande70.8%—

Math Qwen3.8 27B leads

Phi 3 Mini 4k Instruct: 26.6 (#257), Qwen3.8 27B: 37.1 (#161)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
LMArena Math11111456
ProofBench—16%
LiveBench Math15.7%—

Knowledge Qwen3.8 27B leads

Phi 3 Mini 4k Instruct: 28.5 (#246), Qwen3.8 27B: 41.6 (#109)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
LMArena Expert10451482
ARC (AI2) Challenge84.9%—
MMLU68.8%—
OpenBookQA88%—
TriviaQA64%—

Multimodal Not comparable

Phi 3 Mini 4k Instruct: —, Qwen3.8 27B: 41.3 (#37)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
LMArena Vision—1271

Multilingual Qwen3.8 27B leads

Phi 3 Mini 4k Instruct: 26.3 (#280), Qwen3.8 27B: 53.7 (#60)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
LMArena Non-English10211430
LMArena Chinese10211504
LMArena French10761465
LMArena German10441438
LMArena Japanese9351384
LMArena Korean9051393
LMArena Russian10221415
LMArena Spanish10851448

Instruction Following Qwen3.8 27B leads

Phi 3 Mini 4k Instruct: 47.7 (#303), Qwen3.8 27B: 75.8 (#53)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
LMArena Instruction Following10531439
LiveBench Instruction Following39.1%—

Long Context Qwen3.8 27B leads

Phi 3 Mini 4k Instruct: 31.7 (#276), Qwen3.8 27B: 44.3 (#70)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
LMArena Longer Query10441450

Writing & Preference Qwen3.8 27B leads

Phi 3 Mini 4k Instruct: 27.6 (#300), Qwen3.8 27B: 65.8 (#43)

BenchmarkPhi 3 Mini 4k InstructQwen3.8 27B
LMArena Text10731441
LMArena Creative Writing10371384
LMArena Multi-Turn10181441
EQ-Bench Creative Writing—1671
LiveBench Language9.2%—

Frequently asked questions

Is Phi 3 Mini 4k Instruct better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 27.9 on the Noometry Index.

Is Phi 3 Mini 4k Instruct or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 26.6 in the Noometry coding category.

How many benchmarks do Phi 3 Mini 4k Instruct and Qwen3.8 27B share?

17 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen3.8 27B has 31.

Related comparisons

Go deeper