Noometry

Model comparison

GLM-4.5-Air vs GLM-4.6

GLM-4.6 is the stronger model overall, scoring 40.9 to 38.7 on the Noometry Index. GLM-4.5-Air costs 2.4× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

Last verified . 19 shared benchmarks.

GLM-4.5-Air Z.ai (Zhipu)

38.7

Rank #169 Confirmed

GLM-4.6 Z.ai (Zhipu)

40.9

Rank #132 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-4.5-Air scores higher in 1 category and GLM-4.6 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GLM-4.6 leads 39.9 to 34.5.
  • GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
  • GLM-4.6 accepts more context: 205K tokens versus 131K.

Side by side

GLM-4.5-AirGLM-4.6
ProviderZ.ai (Zhipu)Z.ai (Zhipu)
Noometry Index38.740.9
Released2025-07-202025-09-30
WeightsOpenOpen
Context window131K205K
Max output98K131K
Input $ / M tokens$0.20$0.60
Output $ / M tokens$1.10$2.20
Results tracked2729

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

Category by category

Coding GLM-4.6 leads

GLM-4.5-Air: 34.5 (#225), GLM-4.6: 39.9 (#137)

BenchmarkGLM-4.5-AirGLM-4.6
LMArena Coding13971449
SWE-bench Verified (bash only)—55.4%
LMArena WebDev—1339
SciCode—38.4%
GSO2.9%—
ALE-Bench—340.82

Agentic & Tool Use Not comparable

GLM-4.5-Air: —, GLM-4.6: 32.1 (#60)

BenchmarkGLM-4.5-AirGLM-4.6
Terminal-Bench—24.5%
Berkeley Function Calling Leaderboard—72.4%

Reasoning Too close to call

GLM-4.5-Air: 23.3 (#166), GLM-4.6: 23.1 (#168)

BenchmarkGLM-4.5-AirGLM-4.6
Kagi LLM Benchmark43%47.4%
LMArena Hard Prompts13791440
CritPt—1.1%
ForecastBench59.2—

Math GLM-4.6 leads

GLM-4.5-Air: 33.8 (#166), GLM-4.6: 36.4 (#115)

BenchmarkGLM-4.5-AirGLM-4.6
LMArena Math13961431
Omni-MATH39.1%—
FrontierMath (Feb 2025 set)—3.8%
FrontierMath Tier 4 (v1)—2.1%

Knowledge GLM-4.6 leads

GLM-4.5-Air: 34.6 (#184), GLM-4.6: 39.6 (#118)

BenchmarkGLM-4.5-AirGLM-4.6
Vectara Hallucination Rate9.3%9.5%
LMArena Expert13701432
Humanity's Last Exam8.1%—
MMLU-Pro76.2%—
GPQA (HELM)59.4%—

Multilingual GLM-4.6 leads

GLM-4.5-Air: 49.4 (#130), GLM-4.6: 53.6 (#62)

BenchmarkGLM-4.5-AirGLM-4.6
LMArena Non-English13661426
LMArena Chinese14271500
LMArena French13991459
LMArena German13761447
LMArena Japanese13481394
LMArena Korean13061401
LMArena Russian13731418
LMArena Spanish13851436

Instruction Following GLM-4.6 leads

GLM-4.5-Air: 69.8 (#165), GLM-4.6: 74.5 (#93)

BenchmarkGLM-4.5-AirGLM-4.6
LMArena Instruction Following13531410
IFEval81.2%—

Long Context GLM-4.6 leads

GLM-4.5-Air: 41.6 (#130), GLM-4.6: 43.4 (#91)

BenchmarkGLM-4.5-AirGLM-4.6
LMArena Longer Query13671423

Writing & Preference GLM-4.6 leads

GLM-4.5-Air: 56.1 (#134), GLM-4.6: 61.3 (#86)

BenchmarkGLM-4.5-AirGLM-4.6
LMArena Text13841440
LMArena Creative Writing13431411
LMArena Multi-Turn13711427
EQ-Bench Creative Writing—1411
WildBench78.9%—

Frequently asked questions

Is GLM-4.5-Air better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 40.9 to 38.7 on the Noometry Index. GLM-4.5-Air costs 2.4× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

Which is cheaper, GLM-4.5-Air or GLM-4.6?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

Is GLM-4.5-Air or GLM-4.6 better for coding?

GLM-4.6 scores higher on coding benchmarks: 39.9 versus 34.5 in the Noometry coding category.

Which has the bigger context window?

GLM-4.6 does, with 205K tokens against 131K.

How many benchmarks do GLM-4.5-Air and GLM-4.6 share?

19 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and GLM-4.6 has 29.

Related comparisons

Go deeper