Noometry

Model comparison

GLM-4.5 vs GPT-5.1-Codex

GLM-4.5 is the stronger model overall, scoring 41.4 to 38.2 on the Noometry Index.

Last verified . 2 shared benchmarks.

GLM-4.5 Z.ai (Zhipu)

41.4

Rank #125 Confirmed

GPT-5.1-Codex OpenAI

38.2

Rank #178 Reported

Summary

  • They share 2 benchmarks with published results for both. GLM-4.5 scores higher in 1 category and GPT-5.1-Codex in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in math, where GLM-4.5 leads 36.3 to 29.3.
  • The biggest single-benchmark swing is SWE-bench Verified (bash only): 54.2% for GLM-4.5 and 66% for GPT-5.1-Codex.
  • GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
  • GPT-5.1-Codex accepts more context: 400K tokens versus 131K.
  • GLM-4.5 has downloadable open weights; the other is API-only.

Side by side

GLM-4.5GPT-5.1-Codex
ProviderZ.ai (Zhipu)OpenAI
Noometry Index41.438.2
Released2025-07-272025-11-12
WeightsOpenProprietary
Context window131K400K
Max output98K128K
Input $ / M tokens$0.60$1.25
Output $ / M tokens$2.20$10
Results tracked276

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

Category by category

Coding Too close to call

GLM-4.5: 41.1 (#121), GPT-5.1-Codex: 41.7 (#107)

BenchmarkGLM-4.5GPT-5.1-Codex
SWE-bench Verified (bash only)54.2%66%
ALE-Bench344.821,245
LMArena WebDev—1337
WeirdML40.6%—
LMArena Coding1434—
AlgoTune1.52—

Agentic & Tool Use Not comparable

GLM-4.5: —, GPT-5.1-Codex: 37.8 (#32)

BenchmarkGLM-4.5GPT-5.1-Codex
Terminal-Bench—60.4%
METR Time Horizons—70.8%

Reasoning Not comparable

GLM-4.5: 27.7 (#99), GPT-5.1-Codex: —

BenchmarkGLM-4.5GPT-5.1-Codex
Kagi LLM Benchmark57.9%—
LMArena Hard Prompts1430—

Math GLM-4.5 leads

GLM-4.5: 36.3 (#119), GPT-5.1-Codex: 29.3 (#218)

BenchmarkGLM-4.5GPT-5.1-Codex
ProofBench—9%
LMArena Math1427—

Knowledge Not comparable

GLM-4.5: 35.5 (#172), GPT-5.1-Codex: —

BenchmarkGLM-4.5GPT-5.1-Codex
Humanity's Last Exam8.3%—
Confabulations11.3%—
LMArena Expert1433—

Multilingual Not comparable

GLM-4.5: 53.0 (#74), GPT-5.1-Codex: —

BenchmarkGLM-4.5GPT-5.1-Codex
LMArena Non-English1417—
LMArena Chinese1465—
LMArena French1423—
LMArena German1406—
LMArena Japanese1416—
LMArena Korean1382—
LMArena Russian1414—
LMArena Spanish1454—

Instruction Following Not comparable

GLM-4.5: 74.3 (#100), GPT-5.1-Codex: —

BenchmarkGLM-4.5GPT-5.1-Codex
LMArena Instruction Following1405—

Long Context Not comparable

GLM-4.5: 38.2 (#196), GPT-5.1-Codex: —

BenchmarkGLM-4.5GPT-5.1-Codex
Fiction.LiveBench58.3%—
LMArena Longer Query1413—

Writing & Preference Not comparable

GLM-4.5: 57.7 (#121), GPT-5.1-Codex: —

BenchmarkGLM-4.5GPT-5.1-Codex
LMArena Text1430—
LMArena Creative Writing1395—
Short-Story Creative Writing73.4%—
EQ-Bench Creative Writing1343—
LMArena Multi-Turn1415—

Frequently asked questions

Is GLM-4.5 better than GPT-5.1-Codex?

GLM-4.5 is the stronger model overall, scoring 41.4 to 38.2 on the Noometry Index.

Which is cheaper, GLM-4.5 or GPT-5.1-Codex?

GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.

Is GLM-4.5 or GPT-5.1-Codex better for coding?

They score almost the same on coding (41.1 vs 41.7); test both on your own repository before choosing.

Which has the bigger context window?

GPT-5.1-Codex does, with 400K tokens against 131K.

How many benchmarks do GLM-4.5 and GPT-5.1-Codex share?

2 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and GPT-5.1-Codex has 6.

Related comparisons

Go deeper