Noometry

Model comparison

Qwen2.5-Max vs Qwen3-30B-A3B

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 38.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Qwen3-30B-A3B Alibaba (Qwen)

38.9

Rank #179 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Qwen2.5-Max scores higher in 3 categories and Qwen3-30B-A3B in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Qwen2.5-Max leads 41.4 to 31.0.
  • The biggest single-benchmark swing is Confabulations: 21.8% for Qwen2.5-Max and 12.3% for Qwen3-30B-A3B.
  • Qwen3-30B-A3B has downloadable open weights; the other is API-only.

Side by side

Qwen2.5-MaxQwen3-30B-A3B
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index40.738.9
Released2025-01-252025-04-28
WeightsProprietaryOpen
Context window—41K
Max output—16K
Input $ / M tokens—$0.12
Output $ / M tokens—$0.50
Results tracked2732

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

Category by category

Coding Qwen2.5-Max leads

Qwen2.5-Max: 41.8 (#117), Qwen3-30B-A3B: 37.5 (#194)

BenchmarkQwen2.5-MaxQwen3-30B-A3B
LMArena Coding13591416
SciCode—33.3%
WeirdML—29.8%
LiveBench Coding64.4%—

Agentic & Tool Use Not comparable

Qwen2.5-Max: —, Qwen3-30B-A3B: 29.8 (#82)

BenchmarkQwen2.5-MaxQwen3-30B-A3B
Berkeley Function Calling Leaderboard—41.4%

Reasoning Qwen2.5-Max leads

Qwen2.5-Max: 25.6 (#147), Qwen3-30B-A3B: 22.2 (#204)

BenchmarkQwen2.5-MaxQwen3-30B-A3B
LMArena Hard Prompts13601398
Epoch Capabilities Index132.53139.63
Kagi LLM Benchmark—54.9%
CritPt—0.3%
Chess Puzzles—8%
LiveBench Reasoning51.4%—
DTBench—69.3%
LiveBench Data Analysis67.9%—
LMCA—22.4%
LiveBench62.3%—

Math Too close to call

Qwen2.5-Max: 36.9 (#162), Qwen3-30B-A3B: 37.4 (#157)

BenchmarkQwen2.5-MaxQwen3-30B-A3B
LMArena Math13691394
MathArena Final-Answer Competitions—47.8%
OTIS Mock AIME 2024-2025—70.3%
LiveBench Math58.4%—

Knowledge Qwen3-30B-A3B leads

Qwen2.5-Max: 35.3 (#186), Qwen3-30B-A3B: 41.8 (#105)

BenchmarkQwen2.5-MaxQwen3-30B-A3B
Confabulations21.8%12.3%
LMArena Expert13371396
GPQA Diamond—70.1%

Multilingual Qwen3-30B-A3B leads

Qwen2.5-Max: 48.1 (#146), Qwen3-30B-A3B: 49.5 (#132)

BenchmarkQwen2.5-MaxQwen3-30B-A3B
LMArena Non-English13521372
LMArena Chinese13821433
LMArena French13961418
LMArena German13501380
LMArena Japanese13001337
LMArena Korean13041331
LMArena Russian13531370
LMArena Spanish13771404

Instruction Following Too close to call

Qwen2.5-Max: 71.3 (#152), Qwen3-30B-A3B: 72.0 (#142)

BenchmarkQwen2.5-MaxQwen3-30B-A3B
LMArena Instruction Following13351363
LiveBench Instruction Following75.3%—

Long Context Qwen2.5-Max leads

Qwen2.5-Max: 41.4 (#142), Qwen3-30B-A3B: 31.0 (#283)

BenchmarkQwen2.5-MaxQwen3-30B-A3B
LMArena Longer Query13581379
Fiction.LiveBench—40.6%

Writing & Preference Too close to call

Qwen2.5-Max: 55.4 (#146), Qwen3-30B-A3B: 55.6 (#143)

BenchmarkQwen2.5-MaxQwen3-30B-A3B
LMArena Text13671384
LMArena Creative Writing13391317
Short-Story Creative Writing72.9%75.3%
LMArena Multi-Turn13641378
LiveBench Language56.3%—

Frequently asked questions

Is Qwen2.5-Max better than Qwen3-30B-A3B?

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 38.9 on the Noometry Index.

Is Qwen2.5-Max or Qwen3-30B-A3B better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 37.5 in the Noometry coding category.

How many benchmarks do Qwen2.5-Max and Qwen3-30B-A3B share?

20 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper