Noometry

Model comparison

GLM-5.3-Flash vs Qwen2-72B

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 30.0 on the Noometry Index.

Last verified . 19 shared benchmarks.

GLM-5.3-Flash Z.ai (Zhipu)

51.8

Rank #41 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-5.3-Flash scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-5.3-Flash leads 58.4 to 21.2.
  • The biggest single-benchmark swing is GPQA Diamond: 90.2% for GLM-5.3-Flash and 40.8% for Qwen2-72B.

Side by side

GLM-5.3-FlashQwen2-72B
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index51.830.0
Released2026-08-202024-06-07
WeightsOpenOpen
Context window1M—
Max output131K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.50—
Results tracked4026

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), Qwen2-72B: 29.1 (#310)

BenchmarkGLM-5.3-FlashQwen2-72B
LMArena Coding15081196
DeepSWE63.4%—
FrontierCode31.8%—
CursorBench36.8%—
LMArena WebDev1609—
FrontierSWE18.1%—
SciCode51.6%—
WeirdML—11.3%
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
ALE-Bench303.55—

Agentic & Tool Use GLM-5.3-Flash leads

GLM-5.3-Flash: 34.2 (#47), Qwen2-72B: 17.0 (#146)

BenchmarkGLM-5.3-FlashQwen2-72B
APEX-Agents52.8%—
TheAgentCompany—1.1%
GDP.pdf14%—
METR Time Horizons—29.9%

Reasoning GLM-5.3-Flash leads

GLM-5.3-Flash: 48.0 (#42), Qwen2-72B: 23.2 (#181)

BenchmarkGLM-5.3-FlashQwen2-72B
LMArena Hard Prompts14911191
Epoch Capabilities Index151.88125.28
ARC-AGI-265.8%—
ARC-AGI-191%—
CritPt15.4%—
Chess Puzzles14%—
Mystery Game Puzzles8%—
Surface Evolver Bench52.5%—
Bench to the Future 30.15—

Math GLM-5.3-Flash leads

GLM-5.3-Flash: 53.3 (#47), Qwen2-72B: 30.2 (#236)

BenchmarkGLM-5.3-FlashQwen2-72B
LMArena Math15001235
FrontierMath (Tiers 1-3)55.8%—
FrontierMath Tier 417.1%—
OTIS Mock AIME 2024-202593.9%—
ProofBench21%—
MATH Level 5—39.1%

Knowledge GLM-5.3-Flash leads

GLM-5.3-Flash: 58.4 (#36), Qwen2-72B: 21.2 (#275)

BenchmarkGLM-5.3-FlashQwen2-72B
GPQA Diamond90.2%40.8%
LMArena Expert15131171
MMLU—82.4%

Multimodal Not comparable

GLM-5.3-Flash: 42.8 (#27), Qwen2-72B: —

BenchmarkGLM-5.3-FlashQwen2-72B
LMArena Vision1296—

Multilingual GLM-5.3-Flash leads

GLM-5.3-Flash: 56.0 (#25), Qwen2-72B: 35.9 (#244)

BenchmarkGLM-5.3-FlashQwen2-72B
LMArena Non-English14621176
LMArena Chinese15271240
LMArena French14961170
LMArena German14701151
LMArena Japanese14291111
LMArena Korean14461083
LMArena Russian14691169
LMArena Spanish14711169

Instruction Following GLM-5.3-Flash leads

GLM-5.3-Flash: 77.5 (#20), Qwen2-72B: 61.7 (#241)

BenchmarkGLM-5.3-FlashQwen2-72B
LMArena Instruction Following14781181

Long Context GLM-5.3-Flash leads

GLM-5.3-Flash: 45.4 (#39), Qwen2-72B: 36.1 (#235)

BenchmarkGLM-5.3-FlashQwen2-72B
LMArena Longer Query14821192

Writing & Preference GLM-5.3-Flash leads

GLM-5.3-Flash: 65.3 (#50), Qwen2-72B: 40.8 (#241)

BenchmarkGLM-5.3-FlashQwen2-72B
LMArena Text14711203
LMArena Creative Writing14421181
LMArena Multi-Turn14671196

Frequently asked questions

Is GLM-5.3-Flash better than Qwen2-72B?

GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 30.0 on the Noometry Index.

Is GLM-5.3-Flash or Qwen2-72B better for coding?

GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 29.1 in the Noometry coding category.

How many benchmarks do GLM-5.3-Flash and Qwen2-72B share?

19 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper