Noometry

Model comparison

GLM-4.5 vs Inkling-Small

Inkling-Small is the stronger model overall, scoring 46.5 to 42.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

GLM-4.5 Z.ai (Zhipu)

42.0

Rank #122 Confirmed

Inkling-Small Thinking Machines Lab

46.5

Rank #63 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GLM-4.5 scores higher in 2 categories and Inkling-Small in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Inkling-Small leads 48.2 to 35.9.
  • Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
  • Inkling-Small accepts more context: 524K tokens versus 131K.

Side by side

GLM-4.5Inkling-Small
ProviderZ.ai (Zhipu)Thinking Machines Lab
Noometry Index42.046.5
Released2025-07-272026-07-15
WeightsOpenOpen
Context window131K524K
Max output98K1.05M
Input $ / M tokens$0.60$0.45
Output $ / M tokens$2.20$1.20
Results tracked2733

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

Category by category

Coding Inkling-Small leads

GLM-4.5: 41.4 (#125), Inkling-Small: 43.6 (#85)

BenchmarkGLM-4.5Inkling-Small
LMArena Coding14341451
SWE-bench Verified (bash only)54.2%—
LMArena WebDev—1409
SciCode—48.7%
WeirdML40.6%—
ALE-Bench344.82—
AlgoTune1.52—

Reasoning Inkling-Small leads

GLM-4.5: 28.6 (#100), Inkling-Small: 38.6 (#63)

BenchmarkGLM-4.5Inkling-Small
LMArena Hard Prompts14291423
ARC-AGI-2—40.1%
Kagi LLM Benchmark57.9%—
ARC-AGI-1—84%
CritPt—8.3%
Chess Puzzles—18%
Mystery Game Puzzles—6%
Epoch Capabilities Index—150.15

Math Inkling-Small leads

GLM-4.5: 39.0 (#116), Inkling-Small: 45.1 (#77)

BenchmarkGLM-4.5Inkling-Small
LMArena Math14271459
FrontierMath (Tiers 1-3)—46.3%
FrontierMath Tier 4—17.1%
OTIS Mock AIME 2024-2025—90%
ProofBench—6%

Knowledge Inkling-Small leads

GLM-4.5: 35.9 (#179), Inkling-Small: 48.2 (#77)

BenchmarkGLM-4.5Inkling-Small
LMArena Expert14331442
GPQA Diamond—88.5%
Humanity's Last Exam8.3%—
SimpleQA Verified—19.1%
Confabulations11.3%—

Multimodal Not comparable

GLM-4.5: —, Inkling-Small: 39.1 (#62)

BenchmarkGLM-4.5Inkling-Small
LMArena Vision—1235

Multilingual GLM-4.5 leads

GLM-4.5: 52.8 (#77), Inkling-Small: 51.7 (#104)

BenchmarkGLM-4.5Inkling-Small
LMArena Non-English14171402
LMArena Chinese14651465
LMArena French14181436
LMArena German14071405
LMArena Japanese14151405
LMArena Korean13801363
LMArena Russian14141391
LMArena Spanish14541428

Instruction Following Too close to call

GLM-4.5: 74.1 (#104), Inkling-Small: 73.8 (#114)

BenchmarkGLM-4.5Inkling-Small
LMArena Instruction Following14041399

Long Context Inkling-Small leads

GLM-4.5: 38.2 (#201), Inkling-Small: 42.7 (#118)

BenchmarkGLM-4.5Inkling-Small
LMArena Longer Query14121401
Fiction.LiveBench58.3%—

Writing & Preference Inkling-Small leads

GLM-4.5: 57.5 (#127), Inkling-Small: 59.6 (#107)

BenchmarkGLM-4.5Inkling-Small
LMArena Text14301414
LMArena Creative Writing13951331
EQ-Bench Creative Writing13431491
LMArena Multi-Turn14151418
Short-Story Creative Writing73.4%—

Frequently asked questions

Is GLM-4.5 better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 42.0 on the Noometry Index.

Which is cheaper, GLM-4.5 or Inkling-Small?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.

Is GLM-4.5 or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 41.4 in the Noometry coding category.

Which has the bigger context window?

Inkling-Small does, with 524K tokens against 131K.

How many benchmarks do GLM-4.5 and Inkling-Small share?

18 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Inkling-Small has 33.

Related comparisons

Go deeper