Noometry

Model comparison

GLM-4.6V vs GLM-5

GLM-5 is the stronger model overall, scoring 45.9 to 40.9 on the Noometry Index. GLM-4.6V costs 3.4× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

Last verified . 11 shared benchmarks.

GLM-4.6V Z.ai (Zhipu)

40.9

Rank #133 Confirmed

GLM-5 Z.ai (Zhipu)

45.9

Rank #59 Confirmed

Summary

  • They share 11 benchmarks with published results for both. GLM-4.6V scores higher in 0 categories and GLM-5 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-5 leads 52.2 to 37.4.
  • GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $1 / $3.20 for GLM-5.
  • GLM-5 accepts more context: 205K tokens versus 128K.

Side by side

GLM-4.6VGLM-5
ProviderZ.ai (Zhipu)Z.ai (Zhipu)
Noometry Index40.945.9
Released2025-12-082026-02-11
WeightsOpenOpen
Context window128K205K
Max output33K131K
Input $ / M tokens$0.30$1
Output $ / M tokens$0.90$3.20
Results tracked1245

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

Category by category

Coding GLM-5 leads

GLM-4.6V: 40.2 (#128), GLM-5: 49.0 (#47)

BenchmarkGLM-4.6VGLM-5
LMArena Coding13901461
SWE-bench Verified—72.1%
SWE-bench Verified (bash only)—72.8%
LMArena WebDev—1434
SWE-bench Multilingual—69.7%
WeirdML—48.2%
ALE-Bench—765.62

Agentic & Tool Use Not comparable

GLM-4.6V: —, GLM-5: 30.9 (#65)

BenchmarkGLM-4.6VGLM-5
Terminal-Bench—52.4%
τ²-bench Airline—82.5%
τ²-bench Banking—9.8%
τ²-bench Retail—73.7%
τ²-bench Telecom—86.8%
Vending-Bench 2—4,432

Reasoning GLM-5 leads

GLM-4.6V: 26.5 (#117), GLM-5: 27.6 (#100)

BenchmarkGLM-4.6VGLM-5
LMArena Hard Prompts13681451
ARC-AGI-2—4.9%
SimpleBench—53.2%
Kagi LLM Benchmark—75%
NYT Connections (extended)—74.8%
ARC-AGI-1—44.7%
Chess Puzzles—10%
Epoch Capabilities Index—145.84
ForecastBench—61

Math Not comparable

GLM-4.6V: —, GLM-5: 44.8 (#66)

BenchmarkGLM-4.6VGLM-5
MathArena Final-Answer Competitions—65.7%
OTIS Mock AIME 2024-2025—80%
LMArena Math—1440
FrontierMath (Feb 2025 set)—16.4%
FrontierMath Tier 4 (v1)—2.1%

Knowledge GLM-5 leads

GLM-4.6V: 37.4 (#148), GLM-5: 52.2 (#59)

BenchmarkGLM-4.6VGLM-5
LMArena Expert13721454
GPQA Diamond—87.8%
Vectara Hallucination Rate—10.1%

Multimodal Not comparable

GLM-4.6V: 34.2 (#83), GLM-5: —

BenchmarkGLM-4.6VGLM-5
LMArena Vision1164—

Multilingual GLM-5 leads

GLM-4.6V: 48.8 (#135), GLM-5: 53.9 (#57)

BenchmarkGLM-4.6VGLM-5
LMArena Non-English13591430
LMArena Chinese14261511
LMArena Russian13411436
LMArena French—1455
LMArena German—1445
LMArena Japanese—1416
LMArena Korean—1421
LMArena Spanish—1452

Instruction Following GLM-5 leads

GLM-4.6V: 71.6 (#145), GLM-5: 75.4 (#64)

BenchmarkGLM-4.6VGLM-5
LMArena Instruction Following13511427

Long Context GLM-5 leads

GLM-4.6V: 41.3 (#138), GLM-5: 44.6 (#58)

BenchmarkGLM-4.6VGLM-5
LMArena Longer Query13581446
CL-bench—18.7%

Writing & Preference GLM-5 leads

GLM-4.6V: 56.8 (#132), GLM-5: 66.2 (#38)

BenchmarkGLM-4.6VGLM-5
LMArena Text13771446
LMArena Creative Writing13471438
LMArena Multi-Turn13591456
EQ-Bench Creative Writing—1601

Frequently asked questions

Is GLM-4.6V better than GLM-5?

GLM-5 is the stronger model overall, scoring 45.9 to 40.9 on the Noometry Index. GLM-4.6V costs 3.4× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.

Which is cheaper, GLM-4.6V or GLM-5?

GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; GLM-5 lists at $1 and $3.20.

Is GLM-4.6V or GLM-5 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 40.2 in the Noometry coding category.

Which has the bigger context window?

GLM-5 does, with 205K tokens against 128K.

How many benchmarks do GLM-4.6V and GLM-5 share?

11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and GLM-5 has 45.

Related comparisons

Go deeper