Noometry

Model comparison

Phi 3 Mini 128k Instruct vs Qwen3.8 Max

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.7 on the Noometry Index.

Last verified . 17 shared benchmarks.

Phi 3 Mini 128k Instruct Microsoft

29.7

Rank #305 Confirmed

Qwen3.8 Max Alibaba (Qwen)

56.8

Rank #22 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.8 Max leads 73.2 to 31.6.
  • Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.

Side by side

Phi 3 Mini 128k InstructQwen3.8 Max
ProviderMicrosoftAlibaba (Qwen)
Noometry Index29.756.8
Released2024-04-232026-08-02
WeightsOpenProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked1939

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

Category by category

Coding Qwen3.8 Max leads

Phi 3 Mini 128k Instruct: 28.8 (#312), Qwen3.8 Max: 53.5 (#29)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
LMArena Coding10391502
DeepSWE—57.5%
LMArena WebDev—1674
FrontierSWE—17.8%
SciCode—53.2%
BigCodeBench Instruct29.6%—
BigCodeBench Complete40.6%—

Agentic & Tool Use Not comparable

Phi 3 Mini 128k Instruct: —, Qwen3.8 Max: 45.4 (#14)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
APEX-Agents—63.3%
τ²-bench Banking—55.1%
GDP.pdf—23.2%

Reasoning Qwen3.8 Max leads

Phi 3 Mini 128k Instruct: 19.6 (#256), Qwen3.8 Max: 54.4 (#26)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
LMArena Hard Prompts10281496
NYT Connections (extended)—88.3%
CritPt—20%
Chess Puzzles—40%
Mystery Game Puzzles—38%
DTBench—92%
LMCA—46.2%
Epoch Capabilities Index—156.41

Math Qwen3.8 Max leads

Phi 3 Mini 128k Instruct: 31.6 (#222), Qwen3.8 Max: 73.2 (#20)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
LMArena Math10891499
FrontierMath (Tiers 1-3)—74.7%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—100%
ProofBench—58%

Knowledge Qwen3.8 Max leads

Phi 3 Mini 128k Instruct: 26.8 (#254), Qwen3.8 Max: 61.7 (#27)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
LMArena Expert9841507
GPQA Diamond—92.7%
SimpleQA Verified—47.3%

Multimodal Not comparable

Phi 3 Mini 128k Instruct: —, Qwen3.8 Max: 37.2 (#75)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
LMArena Vision—1314
Furniture Assembly—20%

Multilingual Qwen3.8 Max leads

Phi 3 Mini 128k Instruct: 25.2 (#285), Qwen3.8 Max: 56.7 (#18)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
LMArena Non-English10001472
LMArena Chinese10161538
LMArena French10391503
LMArena German10061483
LMArena Japanese8991467
LMArena Korean8561461
LMArena Russian10041481
LMArena Spanish10591492

Instruction Following Qwen3.8 Max leads

Phi 3 Mini 128k Instruct: 51.8 (#294), Qwen3.8 Max: 77.6 (#17)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
LMArena Instruction Following10231479

Long Context Qwen3.8 Max leads

Phi 3 Mini 128k Instruct: 30.4 (#289), Qwen3.8 Max: 45.6 (#31)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
LMArena Longer Query9961489

Writing & Preference Qwen3.8 Max leads

Phi 3 Mini 128k Instruct: 27.1 (#301), Qwen3.8 Max: 67.1 (#30)

BenchmarkPhi 3 Mini 128k InstructQwen3.8 Max
LMArena Text10501483
LMArena Creative Writing10241479
LMArena Multi-Turn9891489

Frequently asked questions

Is Phi 3 Mini 128k Instruct better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.7 on the Noometry Index.

Is Phi 3 Mini 128k Instruct or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 28.8 in the Noometry coding category.

How many benchmarks do Phi 3 Mini 128k Instruct and Qwen3.8 Max share?

17 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen3.8 Max has 39.

Related comparisons

Go deeper