Noometry

Model comparison

GLM-5.3-Flash vs Step 3.7 Flash

GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 36.5 on the Noometry Index.

Last verified . 3 shared benchmarks.

GLM-5.3-Flash Z.ai (Zhipu)

49.6

Rank #45 Confirmed

Step 3.7 Flash StepFun

36.5

Rank #207 Reported

Summary

  • They share 3 benchmarks with published results for both. GLM-5.3-Flash scores higher in 3 categories and Step 3.7 Flash in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GLM-5.3-Flash leads 53.7 to 39.4.
  • The biggest single-benchmark swing is CritPt: 15.4% for GLM-5.3-Flash and 2.3% for Step 3.7 Flash.
  • GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
  • GLM-5.3-Flash accepts more context: 1M tokens versus 256K.

Side by side

GLM-5.3-FlashStep 3.7 Flash
ProviderZ.ai (Zhipu)StepFun
Noometry Index49.636.5
Released2026-08-202026-05-29
WeightsOpenOpen
Context window1M256K
Max output131K256K
Input $ / M tokens$0.15$0.18
Output $ / M tokens$0.50$1.11
Results tracked365

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: 53.7 (#26), Step 3.7 Flash: 39.4 (#147)

BenchmarkGLM-5.3-FlashStep 3.7 Flash
SciCode51.6%40%
ALE-Bench303.55694.12
DeepSWE63.4%—
FrontierCode31.8%—
LMArena WebDev1614—
LMArena Coding1506—

Agentic & Tool Use Not comparable

GLM-5.3-Flash: 34.3 (#41), Step 3.7 Flash: —

BenchmarkGLM-5.3-FlashStep 3.7 Flash
APEX-Agents52.8%—
GDP.pdf14%—

Reasoning GLM-5.3-Flash leads

GLM-5.3-Flash: 31.7 (#69), Step 3.7 Flash: 20.9 (#211)

BenchmarkGLM-5.3-FlashStep 3.7 Flash
CritPt15.4%2.3%
NYT Connections (extended)—39.7%
Chess Puzzles14%—
LMArena Hard Prompts1490—
Mystery Game Puzzles8%—
Surface Evolver Bench52.5%—
Bench to the Future 30.15—
Epoch Capabilities Index151.9—

Math GLM-5.3-Flash leads

GLM-5.3-Flash: 53.1 (#38), Step 3.7 Flash: 40.9 (#74)

BenchmarkGLM-5.3-FlashStep 3.7 Flash
FrontierMath (Tiers 1-3)55.8%—
FrontierMath Tier 417.1%—
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-202593.9%—
ProofBench21%—
LMArena Math1499—

Knowledge Not comparable

GLM-5.3-Flash: 58.4 (#33), Step 3.7 Flash: —

BenchmarkGLM-5.3-FlashStep 3.7 Flash
GPQA Diamond90.2%—
LMArena Expert1512—

Multimodal Not comparable

GLM-5.3-Flash: 42.6 (#25), Step 3.7 Flash: —

BenchmarkGLM-5.3-FlashStep 3.7 Flash
LMArena Vision1304—

Multilingual Not comparable

GLM-5.3-Flash: 56.2 (#24), Step 3.7 Flash: —

BenchmarkGLM-5.3-FlashStep 3.7 Flash
LMArena Non-English1462—
LMArena Chinese1529—
LMArena French1495—
LMArena German1457—
LMArena Japanese1420—
LMArena Korean1443—
LMArena Russian1472—
LMArena Spanish1471—

Instruction Following Not comparable

GLM-5.3-Flash: 77.8 (#17), Step 3.7 Flash: —

BenchmarkGLM-5.3-FlashStep 3.7 Flash
LMArena Instruction Following1480—

Long Context Not comparable

GLM-5.3-Flash: 45.3 (#41), Step 3.7 Flash: —

BenchmarkGLM-5.3-FlashStep 3.7 Flash
LMArena Longer Query1479—

Writing & Preference Not comparable

GLM-5.3-Flash: 65.4 (#49), Step 3.7 Flash: —

BenchmarkGLM-5.3-FlashStep 3.7 Flash
LMArena Text1471—
LMArena Creative Writing1440—
LMArena Multi-Turn1471—

Frequently asked questions

Is GLM-5.3-Flash better than Step 3.7 Flash?

GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 36.5 on the Noometry Index.

Which is cheaper, GLM-5.3-Flash or Step 3.7 Flash?

GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.

Is GLM-5.3-Flash or Step 3.7 Flash better for coding?

GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 39.4 in the Noometry coding category.

Which has the bigger context window?

GLM-5.3-Flash does, with 1M tokens against 256K.

How many benchmarks do GLM-5.3-Flash and Step 3.7 Flash share?

3 benchmarks have published results for both models. GLM-5.3-Flash has 36 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper