Noometry

Model comparison

GLM-5.3 vs Inkling

GLM-5.3 is the stronger model overall, scoring 54.8 to 44.1 on the Noometry Index.

Last verified . 36 shared benchmarks.

GLM-5.3 Z.ai (Zhipu)

54.8

Rank #26 Confirmed

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Summary

  • They share 36 benchmarks with published results for both. GLM-5.3 scores higher in 9 categories and Inkling in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-5.3 leads 62.3 to 31.3.
  • The biggest single-benchmark swing is ProofBench: 49% for GLM-5.3 and 0% for Inkling.
  • GLM-5.3 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.87 / $4.68 for Inkling.
  • GLM-5.3 accepts more context: 1M tokens versus 66K.

Side by side

GLM-5.3Inkling
ProviderZ.ai (Zhipu)Thinking Machines Lab
Noometry Index54.844.1
Released2026-08-142026-07-15
WeightsOpenOpen
Context window1M66K
Max output131K66K
Input $ / M tokens$1.40$1.87
Output $ / M tokens$4.40$4.68
Results tracked4241

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

Category by category

Coding GLM-5.3 leads

GLM-5.3: 59.5 (#14), Inkling: 34.5 (#234)

BenchmarkGLM-5.3Inkling
FrontierCode40.1%14%
LMArena WebDev16221413
FrontierSWE30.2%4.1%
SciCode59%47%
WeirdML75.4%32.3%
LMArena Coding14961464
ALE-Bench1,317946
DeepSWE69%—
CursorBench42.6%—

Agentic & Tool Use GLM-5.3 leads

GLM-5.3: 36.4 (#38), Inkling: 29.6 (#85)

BenchmarkGLM-5.3Inkling
APEX-Agents56.6%33.8%
τ²-bench Banking—25%
Vending-Bench 28,164—

Reasoning GLM-5.3 leads

GLM-5.3: 46.1 (#46), Inkling: 40.4 (#56)

BenchmarkGLM-5.3Inkling
CritPt19.1%5.4%
Chess Puzzles21%21%
LMArena Hard Prompts14891451
DTBench87.7%87.5%
LMCA55.5%37.6%
Epoch Capabilities Index155.61148.54
ARC-AGI-2—36.5%
SimpleBench—50%
NYT Connections (extended)74.2%—
ARC-AGI-1—79.5%
Mystery Game Puzzles33%—
Bench to the Future 30.15—

Math GLM-5.3 leads

GLM-5.3: 62.3 (#33), Inkling: 31.3 (#225)

BenchmarkGLM-5.3Inkling
FrontierMath (Tiers 1-3)68.8%33.3%
FrontierMath Tier 429.3%4.9%
OTIS Mock AIME 2024-202591.1%88.9%
ProofBench49%0%
LMArena Math14891479

Knowledge GLM-5.3 leads

GLM-5.3: 58.3 (#37), Inkling: 55.1 (#49)

BenchmarkGLM-5.3Inkling
GPQA Diamond90.9%88.3%
SimpleQA Verified41%40.3%
LMArena Expert15161465

Multilingual GLM-5.3 leads

GLM-5.3: 55.7 (#28), Inkling: 54.0 (#52)

BenchmarkGLM-5.3Inkling
LMArena Non-English14571434
LMArena Chinese15281490
LMArena French14991458
LMArena German14991446
LMArena Japanese14531429
LMArena Korean14721404
LMArena Russian14631429
LMArena Spanish14601448

Instruction Following GLM-5.3 leads

GLM-5.3: 77.5 (#23), Inkling: 75.1 (#71)

BenchmarkGLM-5.3Inkling
LMArena Instruction Following14771426

Long Context GLM-5.3 leads

GLM-5.3: 45.4 (#41), Inkling: 43.8 (#86)

BenchmarkGLM-5.3Inkling
LMArena Longer Query14821434

Writing & Preference GLM-5.3 leads

GLM-5.3: 75.7 (#6), Inkling: 65.2 (#51)

BenchmarkGLM-5.3Inkling
LMArena Text14711441
LMArena Creative Writing14571387
EQ-Bench Creative Writing20751611
LMArena Multi-Turn14721436
EQ-Bench 4—1226

Frequently asked questions

Is GLM-5.3 better than Inkling?

GLM-5.3 is the stronger model overall, scoring 54.8 to 44.1 on the Noometry Index.

Which is cheaper, GLM-5.3 or Inkling?

GLM-5.3 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Inkling lists at $1.87 and $4.68.

Is GLM-5.3 or Inkling better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.5 versus 34.5 in the Noometry coding category.

Which has the bigger context window?

GLM-5.3 does, with 1M tokens against 66K.

How many benchmarks do GLM-5.3 and Inkling share?

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

Related comparisons

Go deeper