Noometry

Model comparison

GLM-4.7 vs GPT-6 Luna

GPT-6 Luna is the stronger model overall, scoring 53.3 to 42.0 on the Noometry Index.

Last verified . 27 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GLM-4.7 scores higher in 3 categories and GPT-6 Luna in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 38.6.
  • The biggest single-benchmark swing is ProofBench: 6% for GLM-4.7 and 64% for GPT-6 Luna.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 205K.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

GLM-4.7GPT-6 Luna
ProviderZ.ai (Zhipu)OpenAI
Noometry Index42.053.3
Released2025-12-222026-09-22
WeightsOpenProprietary
Context window205K1.05M
Max output131K128K
Input $ / M tokens$0.60$0.10
Output $ / M tokens$2.20$0.50
Results tracked3642

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

Category by category

Coding GPT-6 Luna leads

GLM-4.7: 44.0 (#79), GPT-6 Luna: 55.5 (#25)

BenchmarkGLM-4.7GPT-6 Luna
LMArena WebDev14351581
SciCode45.1%54.6%
LMArena Coding14541439
ALE-Bench399.481,577
DeepSWE—66.6%
FrontierCode—42.4%

Agentic & Tool Use GPT-6 Luna leads

GLM-4.7: 26.5 (#103), GPT-6 Luna: 33.3 (#54)

BenchmarkGLM-4.7GPT-6 Luna
Terminal-Bench33.4%—
APEX-Agents—44.3%
GDP.pdf—23%
Vending-Bench 22,377—

Reasoning GPT-6 Luna leads

GLM-4.7: 24.3 (#164), GPT-6 Luna: 48.2 (#41)

BenchmarkGLM-4.7GPT-6 Luna
CritPt1.7%19.4%
Chess Puzzles6%31%
LMArena Hard Prompts14431411
Epoch Capabilities Index143.51156.28
ARC-AGI-2—59.3%
SimpleBench47.7%—
NYT Connections (extended)—68.7%
ARC-AGI-1—86.7%
Mystery Game Puzzles—7%
DTBench—90.1%
LMCA—44.5%

Math GPT-6 Luna leads

GLM-4.7: 38.6 (#135), GPT-6 Luna: 76.1 (#15)

BenchmarkGLM-4.7GPT-6 Luna
OTIS Mock AIME 2024-202583.3%98.9%
ProofBench6%64%
LMArena Math14231416
FrontierMath (Tiers 1-3)—78.9%
FrontierMath Tier 4—56.1%
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge GPT-6 Luna leads

GLM-4.7: 47.0 (#80), GPT-6 Luna: 57.0 (#41)

BenchmarkGLM-4.7GPT-6 Luna
GPQA Diamond83.3%90.5%
SimpleQA Verified32.2%41.4%
LMArena Expert14241444
Vectara Hallucination Rate11.7%—

Multimodal Not comparable

GLM-4.7: —, GPT-6 Luna: 42.4 (#30)

BenchmarkGLM-4.7GPT-6 Luna
LMArena Vision—1217
Blueprint-Bench 2—31.2%
Furniture Assembly—44.2%

Multilingual GLM-4.7 leads

GLM-4.7: 52.8 (#79), GPT-6 Luna: 50.5 (#117)

BenchmarkGLM-4.7GPT-6 Luna
LMArena Non-English14171386
LMArena Chinese14951433
LMArena French14321420
LMArena German14241369
LMArena Japanese14391369
LMArena Korean13991360
LMArena Russian14231394
LMArena Spanish14341393

Instruction Following Too close to call

GLM-4.7: 74.4 (#95), GPT-6 Luna: 74.3 (#99)

BenchmarkGLM-4.7GPT-6 Luna
LMArena Instruction Following14111409

Long Context Too close to call

GLM-4.7: 42.8 (#116), GPT-6 Luna: 43.0 (#111)

BenchmarkGLM-4.7GPT-6 Luna
LMArena Longer Query14321409
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 60.9 (#93), GPT-6 Luna: 58.3 (#119)

BenchmarkGLM-4.7GPT-6 Luna
LMArena Text14351391
LMArena Creative Writing14011363
LMArena Multi-Turn14461396
EQ-Bench Creative Writing1413—

Frequently asked questions

Is GLM-4.7 better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 42.0 on the Noometry Index.

Which is cheaper, GLM-4.7 or GPT-6 Luna?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

Is GLM-4.7 or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 44.0 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 205K.

How many benchmarks do GLM-4.7 and GPT-6 Luna share?

27 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and GPT-6 Luna has 42.

Related comparisons

Go deeper