Noometry

Model comparison

phi-3-medium 14B vs Qwen3 Max

Qwen3 Max is the stronger model overall, scoring 43.7 to 29.7 on the Noometry Index.

Last verified . 3 shared benchmarks.

phi-3-medium 14B Microsoft

29.7

Rank #306 Reported

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 3 benchmarks with published results for both. phi-3-medium 14B scores higher in 0 categories and Qwen3 Max in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 9.1.
  • The biggest single-benchmark swing is MATH Level 5: 17.6% for phi-3-medium 14B and 97.1% for Qwen3 Max.
  • phi-3-medium 14B has downloadable open weights; the other is API-only.

Side by side

phi-3-medium 14BQwen3 Max
ProviderMicrosoftAlibaba (Qwen)
Noometry Index29.743.7
Released2024-04-232025-09-23
WeightsOpenProprietary
Context window—262K
Max output—66K
Input $ / M tokens—$1.20
Output $ / M tokens—$6
Results tracked1333

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

Category by category

Coding Qwen3 Max leads

phi-3-medium 14B: 36.8 (#201), Qwen3 Max: 43.0 (#93)

Benchmarkphi-3-medium 14BQwen3 Max
BigCodeBench Instruct37.6%—
LMArena Coding—1456
BigCodeBench Complete48.7%—
ALE-Bench—370.45

Agentic & Tool Use Not comparable

phi-3-medium 14B: —, Qwen3 Max: —

Benchmarkphi-3-medium 14BQwen3 Max
Vending-Bench 2—71.56

Reasoning Not comparable

phi-3-medium 14B: —, Qwen3 Max: 22.6 (#190)

Benchmarkphi-3-medium 14BQwen3 Max
Epoch Capabilities Index121.23142.38
Kagi LLM Benchmark—72.5%
NYT Connections (extended)—30.1%
Chess Puzzles—4%
LMArena Hard Prompts—1448
Mystery Game Puzzles—5%
DTBench—82.1%
LMCA—28.3%
Adversarial NLI55.8%—
BIG-Bench Hard81.4%—
HellaSwag82.4%—
WinoGrande81.5%—

Math Qwen3 Max leads

phi-3-medium 14B: 27.3 (#250), Qwen3 Max: 38.7 (#131)

Benchmarkphi-3-medium 14BQwen3 Max
MATH Level 517.6%97.1%
FrontierMath (Tiers 1-3)—18.9%
OTIS Mock AIME 2024-2025—73.3%
LMArena Math—1446

Knowledge Qwen3 Max leads

phi-3-medium 14B: 9.1 (#306), Qwen3 Max: 48.1 (#78)

Benchmarkphi-3-medium 14BQwen3 Max
GPQA Diamond27.6%72.6%
SimpleQA Verified—48.7%
LMArena Expert—1455
ARC (AI2) Challenge91.6%—
MMLU78%—
OpenBookQA87.4%—
TriviaQA73.9%—

Multilingual Not comparable

phi-3-medium 14B: —, Qwen3 Max: 53.7 (#62)

Benchmarkphi-3-medium 14BQwen3 Max
LMArena Non-English—1429
LMArena Chinese—1478
LMArena French—1449
LMArena German—1463
LMArena Japanese—1397
LMArena Korean—1399
LMArena Russian—1428
LMArena Spanish—1462

Instruction Following Not comparable

phi-3-medium 14B: —, Qwen3 Max: 74.8 (#87)

Benchmarkphi-3-medium 14BQwen3 Max
LMArena Instruction Following—1419

Long Context Not comparable

phi-3-medium 14B: —, Qwen3 Max: 41.6 (#134)

Benchmarkphi-3-medium 14BQwen3 Max
Fiction.LiveBench—66.7%
CL-bench—14.5%
LMArena Longer Query—1438

Writing & Preference Not comparable

phi-3-medium 14B: —, Qwen3 Max: 62.4 (#76)

Benchmarkphi-3-medium 14BQwen3 Max
LMArena Text—1439
LMArena Creative Writing—1402
LMArena Multi-Turn—1446

Frequently asked questions

Is phi-3-medium 14B better than Qwen3 Max?

Qwen3 Max is the stronger model overall, scoring 43.7 to 29.7 on the Noometry Index.

Is phi-3-medium 14B or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 43.0 versus 36.8 in the Noometry coding category.

How many benchmarks do phi-3-medium 14B and Qwen3 Max share?

3 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper