Enter opens the highlighted result. Esc closes.

GLM 4.7 vs GPT-5.2-Codex

GLM 4.7 leads GPT-5.2-Codex on coding, 55.1 to 45.4 on the Vibe Coding Index, and GLM 4.7 costs 6.4x less per output token ($2.20 vs $14.00 per million). Updated October 22, 2026; 18 benchmarks have a result for both.

Replace GLM 4.7 Replace GPT-5.2-Codex
GLM 4.7Z.ai
Coding
55.1
Overall
56.9
Output $/M
$2.20
6
GPT-5.2-CodexOpenAI
Coding
45.4
Overall
No data
Output $/M
$14.00
12
vs boards won of 18 shared

GLM 4.7 or GPT-5.2-Codex: which to pick

Pick GLM 4.7 for coding: it scores 55.1 on the Vibe Coding Index against 45.4 for GPT-5.2-Codex, though on 2 benchmarks against 3.

Pick GPT-5.2-Codex for a larger context window (400K against 205K tokens) and work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.

Model AGLM 4.7Z.ai55.1/1002 independent benchmarks$0.29 per solved taskModel BGPT-5.2-CodexOpenAI45.4/1003 independent benchmarks$0.43 per solved task
Shared results
18
GLM 4.7 only
63
GPT-5.2-Codex only
4
Like-for-like categories
5 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
GLM 4.7 55.1 from 2 benchmarks, GPT-5.2-Codex 45.4 from 3 benchmarks.
Widest category
Coding, 15.3 points apart on average over 8 shared benchmarks.
Widest single gap
Terminal-Bench: GLM 4.7 33.4% against GPT-5.2-Codex 66.5%, 33.1 points apart on a 0 to 100 scale.
Output price
GLM 4.7 $2.20 against GPT-5.2-Codex $14.00 per million output tokens, 6.4x apart.
Context window
GLM 4.7 takes 205K tokens, GPT-5.2-Codex 400K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGLM 4.7BarsGPT-5.2-CodexTies
Coding35
Intelligence01
Agentic work32
Reasoning02
General02
All shared boards612
CodingLike-for-likeSix of these boards feed the Vibe Coding Index35
Coding benchmarks for GLM 4.7 and GPT-5.2-Codex
BenchmarkGLM 4.7GPT-5.2-CodexLeader
SWE-bench VerifiedNot measured72.8%Only GPT-5.2-Codex measured
SWE-bench MultilingualNot measured66.3%Only GPT-5.2-Codex measured
LMArena WebDev14351339GLM 4.7
AA Coding Index45.3Not measuredOnly GLM 4.7 measured
LiveCodeBench (Vals AI)82.2%88.0%GPT-5.2-Codex
SWE-bench Verified (Vals AI)69.4%72.4%GPT-5.2-Codex
Vibe Code Bench (Vals AI)Not measured37.9%Only GPT-5.2-Codex measured
LiveCodeBench (Artificial Analysis run)89.4%Not measuredOnly GLM 4.7 measured
Terminal-Bench Hard (Artificial Analysis run)31.8%37.1%GPT-5.2-Codex
Terminal-Bench33.4%66.5%GPT-5.2-Codex
ALE-Bench399.51299.9GPT-5.2-Codex
LMArena Text: coding1454Not measuredOnly GLM 4.7 measured
LMArena Text: software and IT1453Not measuredOnly GLM 4.7 measured
LMArena WebDev: React14201329GLM 4.7
LMArena WebDev: HTML14471348GLM 4.7
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GLM 4.7 and GPT-5.2-Codex
BenchmarkGLM 4.7GPT-5.2-CodexLeader
AA Intelligence Index22.228.5GPT-5.2-Codex
Epoch Capabilities Index143.6Not measuredOnly GLM 4.7 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index32
Agentic work benchmarks for GLM 4.7 and GPT-5.2-Codex
BenchmarkGLM 4.7GPT-5.2-CodexLeader
Design Arena: agents building web appsNot measured1051Only GPT-5.2-Codex measured
Design Arena: agents building full-stack apps1050993GLM 4.7
Design Arena: agents building mobile apps11051090GLM 4.7
Design Arena: agents building Android apps11121176GPT-5.2-Codex
Design Arena: agents building Godot games10581142GPT-5.2-Codex
τ²-Bench Telecom95.9%92.1%GLM 4.7
Vending-Bench 2$2,377Not measuredOnly GLM 4.7 measured
BrowseComp-Plus64.7%Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
Reasoning benchmarks for GLM 4.7 and GPT-5.2-Codex
BenchmarkGLM 4.7GPT-5.2-CodexLeader
GPQA Diamond80.0%Not measuredOnly GLM 4.7 measured
GPQA Diamond (Artificial Analysis run)85.9%89.9%GPT-5.2-Codex
Humanity's Last Exam (Artificial Analysis run)27.4%35.7%GPT-5.2-Codex
GPQA Diamond (Epoch AI run)83.3%Not measuredOnly GLM 4.7 measured
SimpleBench47.7%Not measuredOnly GLM 4.7 measured
Chess puzzles21.0%Not measuredOnly GLM 4.7 measured
LMArena Text: hard prompts1443Not measuredOnly GLM 4.7 measured
LMArena Text: expert1424Not measuredOnly GLM 4.7 measured
LMArena Text: hard prompts in English1452Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 13 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Math benchmarks for GLM 4.7 and GPT-5.2-Codex
BenchmarkGLM 4.7GPT-5.2-CodexLeader
AIME93.3%Not measuredOnly GLM 4.7 measured
MGSM (Vals AI)88.2%Not measuredOnly GLM 4.7 measured
AA Math Index95.0Not measuredOnly GLM 4.7 measured
AIME 2025 (Artificial Analysis run)95.0%Not measuredOnly GLM 4.7 measured
OTIS Mock AIME83.3%Not measuredOnly GLM 4.7 measured
ProofBench6.0%Not measuredOnly GLM 4.7 measured
LMArena Text: math1424Not measuredOnly GLM 4.7 measured
LMArena Text: mathematical work1411Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 5 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
Knowledge benchmarks for GLM 4.7 and GPT-5.2-Codex
BenchmarkGLM 4.7GPT-5.2-CodexLeader
MMLU Pro82.7%Not measuredOnly GLM 4.7 measured
LegalBench (Vals AI)83.4%Not measuredOnly GLM 4.7 measured
CaseLaw (Vals AI)54.9%Not measuredOnly GLM 4.7 measured
CorpFin (Vals AI)46.4%Not measuredOnly GLM 4.7 measured
TaxEval (Vals AI)68.8%Not measuredOnly GLM 4.7 measured
MedQA (Vals AI)93.7%Not measuredOnly GLM 4.7 measured
MedCode (Vals AI)32.8%Not measuredOnly GLM 4.7 measured
MMLU Pro (Artificial Analysis run)85.6%Not measuredOnly GLM 4.7 measured
SimpleQA Verified32.2%Not measuredOnly GLM 4.7 measured
LMArena Text: science1457Not measuredOnly GLM 4.7 measured
LMArena Text: medicine and healthcare1469Not measuredOnly GLM 4.7 measured
LMArena Text: legal and government1444Not measuredOnly GLM 4.7 measured
LMArena Text: business and finance1429Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for GLM 4.7 and GPT-5.2-Codex
BenchmarkGLM 4.7GPT-5.2-CodexLeader
Design Arena: websites1225Not measuredOnly GLM 4.7 measured
Design Arena: UI components1196Not measuredOnly GLM 4.7 measured
Design Arena: game dev1188Not measuredOnly GLM 4.7 measured
Design Arena: data viz1195Not measuredOnly GLM 4.7 measured
Design Arena: 3D1190Not measuredOnly GLM 4.7 measured
Design Arena: all code categories1216Not measuredOnly GLM 4.7 measured
Design Arena: SVG1142Not measuredOnly GLM 4.7 measured
Design Arena: ASCII art1165Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
General benchmarks for GLM 4.7 and GPT-5.2-Codex
BenchmarkGLM 4.7GPT-5.2-CodexLeader
MedScribe (Vals AI)68.6%Not measuredOnly GLM 4.7 measured
IFBench67.9%77.6%GPT-5.2-Codex
Long context reasoning (AA-LCR)71.0%82.3%GPT-5.2-Codex
CL-bench15.9%Not measuredOnly GLM 4.7 measured
CL-bench Life10.9%Not measuredOnly GLM 4.7 measured
LMArena Text1435Not measuredOnly GLM 4.7 measured
LMArena Text: instruction following1412Not measuredOnly GLM 4.7 measured
LMArena Text: creative writing1401Not measuredOnly GLM 4.7 measured
LMArena Text: English1453Not measuredOnly GLM 4.7 measured
LMArena Text: non-English1417Not measuredOnly GLM 4.7 measured
LMArena Text: Chinese1495Not measuredOnly GLM 4.7 measured
LMArena Text: German1426Not measuredOnly GLM 4.7 measured
LMArena Text: Japanese1439Not measuredOnly GLM 4.7 measured
LMArena Text: Korean1399Not measuredOnly GLM 4.7 measured
LMArena Text: French1432Not measuredOnly GLM 4.7 measured
LMArena Text: Spanish1434Not measuredOnly GLM 4.7 measured
LMArena Text: Russian1423Not measuredOnly GLM 4.7 measured
LMArena Text: Polish1435Not measuredOnly GLM 4.7 measured
LMArena Text: multi-turn1446Not measuredOnly GLM 4.7 measured
LMArena Text: longer queries1432Not measuredOnly GLM 4.7 measured
LMArena Text: writing and language1411Not measuredOnly GLM 4.7 measured
LMArena Text: entertainment and media1400Not measuredOnly GLM 4.7 measured
Neither model has a result on the other 24 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 4.7 and GPT-5.2-Codex
BenchmarkGLM 4.7GPT-5.2-CodexLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

GLM 4.7$0.0017Fits in one request
GPT-5.2-Codex$0.0088Fits in one request

GLM 4.7 costs less

Repository review

50K input + 3K output tokens

GLM 4.7$0.037Fits in one request
GPT-5.2-Codex$0.130Fits in one request

GLM 4.7 costs less

Agent loop

200K input + 10K output tokens

GLM 4.7$0.142Exceeds the context window
GPT-5.2-Codex$0.490Fits in one request

GLM 4.7 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of GLM 4.7 and GPT-5.2-Codex
SpecificationZ.ai GLM 4.7OpenAI GPT-5.2-Codex
MakerZ.aiOpenAI
WeightsOpen weightsNo public weights listed
ReleasedDecember 22, 2025January 14, 2026
Context window205K400K
Input $/Mtok$0.60$1.75
Output $/Mtok$2.20$14.00
Coding index55.145.4
Independent measurements behind it23
Cost per solved task$0.29$0.43
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.7 better than GPT-5.2-Codex for coding?

Pick GLM 4.7 for coding: it scores 55.1 on the Vibe Coding Index against 45.4 for GPT-5.2-Codex, though on 2 benchmarks against 3. Pick GPT-5.2-Codex for a larger context window (400K against 205K tokens) and work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.

Which is cheaper, GLM 4.7 or GPT-5.2-Codex?

GLM 4.7 costs $0.60 per million input tokens and $2.20 per million output tokens; GPT-5.2-Codex costs $1.75 and $14.00. Per solved SWE-bench Verified task, GLM 4.7 costs $0.29 and GPT-5.2-Codex $0.43.

Which has the bigger context window, GLM 4.7 or GPT-5.2-Codex?

GPT-5.2-Codex, with 400K tokens against 205K.

How many benchmarks is the GLM 4.7 vs GPT-5.2-Codex comparison based on?

18 benchmarks have a result for both models as of October 22, 2026. GLM 4.7's coding index rests on 2 independent benchmarks and GPT-5.2-Codex's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/glm-4-7-vs-gpt-5-2-codex" title="GLM 4.7 vs GPT-5.2-Codex, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/glm-4-7-vs-gpt-5-2-codex">LLMBenchmark.ai, GLM 4.7 vs GPT-5.2-Codex</a></p>