Noometry

Model comparison

Phi-4 vs Qwen3.8 27B

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 31.2 on the Noometry Index. Phi-4 costs 6.9× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.

Last verified . 18 shared benchmarks.

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Qwen3.8 27B Alibaba (Qwen)

46.0

Rank #68 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Phi-4 scores higher in 0 categories and Qwen3.8 27B in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen3.8 27B leads 65.8 to 40.5.
  • Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.04 / $2.30 for Qwen3.8 27B.
  • Qwen3.8 27B accepts more context: 262K tokens versus 128K.

Side by side

Phi-4Qwen3.8 27B
ProviderMicrosoftAlibaba (Qwen)
Noometry Index31.246.0
Released2024-12-112026-08-14
WeightsOpenOpen
Context window128K262K
Max output4K33K
Input $ / M tokens$0.07$0.04
Output $ / M tokens$0.14$2.30
Results tracked3731

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

Category by category

Coding Qwen3.8 27B leads

Phi-4: 34.4 (#239), Qwen3.8 27B: 50.5 (#44)

BenchmarkPhi-4Qwen3.8 27B
LMArena Coding12311482
LMArena WebDev—1593
SciCode—46.6%
BigCodeBench Instruct45.5%—
LiveBench Coding30.7%—
BigCodeBench Complete55.4%—

Agentic & Tool Use Qwen3.8 27B leads

Phi-4: 22.8 (#128), Qwen3.8 27B: 32.9 (#57)

BenchmarkPhi-4Qwen3.8 27B
APEX-Agents—47.5%
Berkeley Function Calling Leaderboard28.8%—
BALROG11.6%—

Reasoning Qwen3.8 27B leads

Phi-4: 17.7 (#291), Qwen3.8 27B: 41.0 (#54)

BenchmarkPhi-4Qwen3.8 27B
LMArena Hard Prompts12201460
Epoch Capabilities Index130.42149.38
ARC-AGI-2—42.4%
NYT Connections (extended)—54.5%
ARC-AGI-1—87.5%
CritPt—5.4%
Chess Puzzles1%—
LiveBench Reasoning47.8%—
DTBench—88%
LiveBench Data Analysis45.2%—
LMCA—41.4%
Surface Evolver Bench—45%
LiveBench41.6%—

Math Qwen3.8 27B leads

Phi-4: 20.8 (#285), Qwen3.8 27B: 37.1 (#161)

BenchmarkPhi-4Qwen3.8 27B
LMArena Math12461456
OTIS Mock AIME 2024-202513.8%—
ProofBench—16%
LiveBench Math42%—
MATH Level 564.9%—

Knowledge Qwen3.8 27B leads

Phi-4: 32.6 (#209), Qwen3.8 27B: 41.6 (#109)

BenchmarkPhi-4Qwen3.8 27B
LMArena Expert12031482
GPQA Diamond56.1%—
Confabulations29.4%—
Vectara Hallucination Rate3.7%—
MMLU84.8%—

Multimodal Not comparable

Phi-4: —, Qwen3.8 27B: 41.3 (#37)

BenchmarkPhi-4Qwen3.8 27B
LMArena Vision—1271

Multilingual Qwen3.8 27B leads

Phi-4: 37.2 (#237), Qwen3.8 27B: 53.7 (#60)

BenchmarkPhi-4Qwen3.8 27B
LMArena Non-English11971430
LMArena Chinese12121504
LMArena French12241465
LMArena German12221438
LMArena Japanese11581384
LMArena Korean11511393
LMArena Russian12091415
LMArena Spanish12341448

Instruction Following Qwen3.8 27B leads

Phi-4: 60.4 (#251), Qwen3.8 27B: 75.8 (#53)

BenchmarkPhi-4Qwen3.8 27B
LMArena Instruction Following12011439
LiveBench Instruction Following58.4%—

Long Context Qwen3.8 27B leads

Phi-4: 36.9 (#226), Qwen3.8 27B: 44.3 (#70)

BenchmarkPhi-4Qwen3.8 27B
LMArena Longer Query12171450

Writing & Preference Qwen3.8 27B leads

Phi-4: 40.5 (#244), Qwen3.8 27B: 65.8 (#43)

BenchmarkPhi-4Qwen3.8 27B
LMArena Text12171441
LMArena Creative Writing11821384
LMArena Multi-Turn12061441
Short-Story Creative Writing62.6%—
EQ-Bench Creative Writing—1671
LiveBench Language25.6%—

Frequently asked questions

Is Phi-4 better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 31.2 on the Noometry Index. Phi-4 costs 6.9× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.

Which is cheaper, Phi-4 or Qwen3.8 27B?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Qwen3.8 27B lists at $0.04 and $2.30.

Is Phi-4 or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

Qwen3.8 27B does, with 262K tokens against 128K.

How many benchmarks do Phi-4 and Qwen3.8 27B share?

18 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen3.8 27B has 31.

Related comparisons

Go deeper