Noometry

Model comparison

GLM-5.3-Flash vs Qwen2.5-Max

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 40.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

GLM-5.3-Flash Z.ai (Zhipu)

51.8

Rank #41 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GLM-5.3-Flash scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-5.3-Flash leads 58.4 to 35.3.
  • GLM-5.3-Flash has downloadable open weights; the other is API-only.

Side by side

GLM-5.3-FlashQwen2.5-Max
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index51.840.7
Released2026-08-202025-01-25
WeightsOpenProprietary
Context window1M—
Max output131K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.50—
Results tracked4027

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

Category by category

Coding GLM-5.3-Flash leads

GLM-5.3-Flash: 53.1 (#31), Qwen2.5-Max: 41.8 (#117)

BenchmarkGLM-5.3-FlashQwen2.5-Max
LMArena Coding15081359
DeepSWE63.4%—
FrontierCode31.8%—
CursorBench36.8%—
LMArena WebDev1609—
FrontierSWE18.1%—
SciCode51.6%—
LiveBench Coding—64.4%
ALE-Bench303.55—

Agentic & Tool Use Not comparable

GLM-5.3-Flash: 34.2 (#47), Qwen2.5-Max: —

BenchmarkGLM-5.3-FlashQwen2.5-Max
APEX-Agents52.8%—
GDP.pdf14%—

Reasoning GLM-5.3-Flash leads

GLM-5.3-Flash: 48.0 (#42), Qwen2.5-Max: 25.6 (#147)

BenchmarkGLM-5.3-FlashQwen2.5-Max
LMArena Hard Prompts14911360
Epoch Capabilities Index151.88132.53
ARC-AGI-265.8%—
ARC-AGI-191%—
CritPt15.4%—
Chess Puzzles14%—
LiveBench Reasoning—51.4%
Mystery Game Puzzles8%—
LiveBench Data Analysis—67.9%
Surface Evolver Bench52.5%—
Bench to the Future 30.15—
LiveBench—62.3%

Math GLM-5.3-Flash leads

GLM-5.3-Flash: 53.3 (#47), Qwen2.5-Max: 36.9 (#162)

BenchmarkGLM-5.3-FlashQwen2.5-Max
LMArena Math15001369
FrontierMath (Tiers 1-3)55.8%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202593.9%—
ProofBench21%—
LiveBench Math—58.4%

Knowledge GLM-5.3-Flash leads

GLM-5.3-Flash: 58.4 (#36), Qwen2.5-Max: 35.3 (#186)

BenchmarkGLM-5.3-FlashQwen2.5-Max
LMArena Expert15131337
GPQA Diamond90.2%—
Confabulations—21.8%

Multimodal Not comparable

GLM-5.3-Flash: 42.8 (#27), Qwen2.5-Max: —

BenchmarkGLM-5.3-FlashQwen2.5-Max
LMArena Vision1296—

Multilingual GLM-5.3-Flash leads

GLM-5.3-Flash: 56.0 (#25), Qwen2.5-Max: 48.1 (#146)

BenchmarkGLM-5.3-FlashQwen2.5-Max
LMArena Non-English14621352
LMArena Chinese15271382
LMArena French14961396
LMArena German14701350
LMArena Japanese14291300
LMArena Korean14461304
LMArena Russian14691353
LMArena Spanish14711377

Instruction Following GLM-5.3-Flash leads

GLM-5.3-Flash: 77.5 (#20), Qwen2.5-Max: 71.3 (#152)

BenchmarkGLM-5.3-FlashQwen2.5-Max
LMArena Instruction Following14781335
LiveBench Instruction Following—75.3%

Long Context GLM-5.3-Flash leads

GLM-5.3-Flash: 45.4 (#39), Qwen2.5-Max: 41.4 (#142)

BenchmarkGLM-5.3-FlashQwen2.5-Max
LMArena Longer Query14821358

Writing & Preference GLM-5.3-Flash leads

GLM-5.3-Flash: 65.3 (#50), Qwen2.5-Max: 55.4 (#146)

BenchmarkGLM-5.3-FlashQwen2.5-Max
LMArena Text14711367
LMArena Creative Writing14421339
LMArena Multi-Turn14671364
Short-Story Creative Writing—72.9%
LiveBench Language—56.3%

Frequently asked questions

Is GLM-5.3-Flash better than Qwen2.5-Max?

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 40.7 on the Noometry Index.

Is GLM-5.3-Flash or Qwen2.5-Max better for coding?

GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 41.8 in the Noometry coding category.

How many benchmarks do GLM-5.3-Flash and Qwen2.5-Max share?

18 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper