Noometry

Model comparison

GLM-5.1 vs GLM-5.3

GLM-5.3 is the stronger model overall, scoring 54.8 to 47.8 on the Noometry Index.

Last verified . 33 shared benchmarks.

GLM-5.1 Z.ai (Zhipu)

47.8

Rank #59 Confirmed

GLM-5.3 Z.ai (Zhipu)

54.8

Rank #26 Confirmed

Summary

  • They share 33 benchmarks with published results for both. GLM-5.1 scores higher in 0 categories and GLM-5.3 in 9 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-5.3 leads 62.3 to 49.7.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 36.8% for GLM-5.1 and 68.8% for GLM-5.3.
  • Both cost about the same: $1.40 input and $4.40 output per million tokens.
  • GLM-5.3 accepts more context: 1M tokens versus 200K.

Side by side

GLM-5.1GLM-5.3
ProviderZ.ai (Zhipu)Z.ai (Zhipu)
Noometry Index47.854.8
Released2026-04-072026-08-14
WeightsOpenOpen
Context window200K1M
Max output131K131K
Input $ / M tokens$1.40$1.40
Output $ / M tokens$4.40$4.40
Results tracked4142

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

Category by category

Coding GLM-5.3 leads

GLM-5.1: 48.7 (#55), GLM-5.3: 59.5 (#14)

BenchmarkGLM-5.1GLM-5.3
LMArena WebDev15081622
SciCode43.8%59%
WeirdML57.1%75.4%
LMArena Coding14851496
ALE-Bench887.11,317
SWE-bench Verified74.2%—
DeepSWE—69%
FrontierCode—40.1%
CursorBench—42.6%
FrontierSWE—30.2%

Agentic & Tool Use GLM-5.3 leads

GLM-5.1: 24.9 (#113), GLM-5.3: 36.4 (#38)

BenchmarkGLM-5.1GLM-5.3
APEX-Agents40.9%56.6%
Vending-Bench 25,6348,164
ExploitBench18.1%—
GBAEval0%—

Reasoning GLM-5.3 leads

GLM-5.1: 39.1 (#60), GLM-5.3: 46.1 (#46)

BenchmarkGLM-5.1GLM-5.3
NYT Connections (extended)77.7%74.2%
CritPt4.6%19.1%
Chess Puzzles19%21%
LMArena Hard Prompts14721489
Epoch Capabilities Index149.84155.61
SimpleBench55.1%—
Thematic Generalization69.8%—
Mystery Game Puzzles—33%
DTBench—87.7%
LMCA—55.5%
Bench to the Future 3—0.15

Math GLM-5.3 leads

GLM-5.1: 49.7 (#60), GLM-5.3: 62.3 (#33)

BenchmarkGLM-5.1GLM-5.3
FrontierMath (Tiers 1-3)36.8%68.8%
OTIS Mock AIME 2024-202593.3%91.1%
ProofBench22.2%49%
LMArena Math14731489
FrontierMath Tier 4—29.3%
MathArena Final-Answer Competitions67.1%—
FrontierMath (Feb 2025 set)33.4%—
FrontierMath Tier 4 (v1)12.5%—

Knowledge GLM-5.3 leads

GLM-5.1: 54.9 (#50), GLM-5.3: 58.3 (#37)

BenchmarkGLM-5.1GLM-5.3
GPQA Diamond89.9%90.9%
SimpleQA Verified34%41%
LMArena Expert14761516

Multilingual Too close to call

GLM-5.1: 55.0 (#36), GLM-5.3: 55.7 (#28)

BenchmarkGLM-5.1GLM-5.3
LMArena Non-English14471457
LMArena Chinese15151528
LMArena French14741499
LMArena German14651499
LMArena Japanese14341453
LMArena Korean14181472
LMArena Russian14541463
LMArena Spanish14691460

Instruction Following GLM-5.3 leads

GLM-5.1: 76.3 (#42), GLM-5.3: 77.5 (#23)

BenchmarkGLM-5.1GLM-5.3
LMArena Instruction Following14511477

Long Context Too close to call

GLM-5.1: 44.9 (#53), GLM-5.3: 45.4 (#41)

BenchmarkGLM-5.1GLM-5.3
LMArena Longer Query14661482

Writing & Preference GLM-5.3 leads

GLM-5.1: 66.9 (#31), GLM-5.3: 75.7 (#6)

BenchmarkGLM-5.1GLM-5.3
LMArena Text14611471
LMArena Creative Writing14531457
EQ-Bench Creative Writing15922075
LMArena Multi-Turn14721472

Frequently asked questions

Is GLM-5.1 better than GLM-5.3?

GLM-5.3 is the stronger model overall, scoring 54.8 to 47.8 on the Noometry Index.

Which is cheaper, GLM-5.1 or GLM-5.3?

GLM-5.3 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

Is GLM-5.1 or GLM-5.3 better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.5 versus 48.7 in the Noometry coding category.

Which has the bigger context window?

GLM-5.3 does, with 1M tokens against 200K.

How many benchmarks do GLM-5.1 and GLM-5.3 share?

33 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GLM-5.3 has 42.

Related comparisons

Go deeper