GLM 5V Turbo vs GPT-5.2-Codex
GPT-5.2-Codex leads GLM 5V Turbo on the Artificial Analysis Intelligence Index, 28.5 to 23.5, and GLM 5V Turbo costs 3.5x less per output token ($4.00 vs $14.00 per million). Updated October 22, 2026; 15 benchmarks have a result for both.
GLM 5V Turbo or GPT-5.2-Codex: which to pick
Only GPT-5.2-Codex has a coding score, 45.4 on the Vibe Coding Index; GLM 5V Turbo has none, so the two cannot be ranked on coding.
Pick GLM 5V Turbo for output tokens 3.5x cheaper ($4.00 vs $14.00 per million) and work measured by LMArena WebDev or LMArena WebDev: React, where it leads.
- Shared results
- 15
- GLM 5V Turbo only
- 50
- GPT-5.2-Codex only
- 7
- 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only GPT-5.2-Codex has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.2-Codex
GPT-5.2-Codex leads, 28.5 against 23.5.
Same board, both measured
Web design
Design Arena: websites
No call
Only GLM 5V Turbo has a Design Arena: websites result, 1230.
Directional only
Long documents
Listed context window
GPT-5.2-Codex
GPT-5.2-Codex takes 400K tokens against 203K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 5V Turbo
GLM 5V Turbo $0.0032, GPT-5.2-Codex $0.0088 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.2-Codex has the number, $0.43.
Directional only
At a glance
- Coding index
- GLM 5V Turbo not benchmarked, GPT-5.2-Codex 45.4 from 3 benchmarks.
- Widest category
- General, 14.3 points apart on average over 2 shared benchmarks.
- Widest single gap
- Design Arena: agents building Godot games: GLM 5V Turbo 957 against GPT-5.2-Codex 1142, 23.1 points apart on a 0 to 100 scale.
- Output price
- GLM 5V Turbo $4.00 against GPT-5.2-Codex $14.00 per million output tokens, 3.5x apart.
- Context window
- GLM 5V Turbo takes 203K 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.
| Category | GLM 5V Turbo | Bars | GPT-5.2-Codex | Ties |
|---|---|---|---|---|
| Coding | 3 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 5 | 1 | ||
| Reasoning | 0 | 2 | ||
| General | 0 | 2 | ||
| All shared boards | 8 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index31
| Benchmark | GLM 5V Turbo | GPT-5.2-Codex | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 72.8% | Only GPT-5.2-Codex measured |
| SWE-bench Multilingual | Not measured | 66.3% | Only GPT-5.2-Codex measured |
| LMArena WebDev | 1402 | 1339 | GLM 5V Turbo |
| LiveCodeBench (Vals AI) | Not measured | 88.0% | Only GPT-5.2-Codex measured |
| SWE-bench Verified (Vals AI) | Not measured | 72.4% | Only GPT-5.2-Codex measured |
| Vibe Code Bench (Vals AI) | Not measured | 37.9% | Only GPT-5.2-Codex measured |
| Terminal-Bench Hard (Artificial Analysis run) | 32.6% | 37.1% | GPT-5.2-Codex |
| Terminal-Bench | Not measured | 66.5% | Only GPT-5.2-Codex measured |
| ALE-Bench | Not measured | 1299.9 | Only GPT-5.2-Codex measured |
| LMArena Text: coding | 1466 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: software and IT | 1460 | Not measured | Only GLM 5V Turbo measured |
| LMArena WebDev: React | 1386 | 1329 | GLM 5V Turbo |
| LMArena WebDev: HTML | 1356 | 1348 | GLM 5V Turbo |
| LMArena WebDev: from an image | 1425 | Not measured | Only GLM 5V Turbo measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 5V Turbo | GPT-5.2-Codex | Leader |
|---|---|---|---|
| AA Intelligence Index | 23.5 | 28.5 | GPT-5.2-Codex |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | GLM 5V Turbo | GPT-5.2-Codex | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1124 | 1051 | GLM 5V Turbo |
| Design Arena: agents building full-stack apps | 1149 | 993 | GLM 5V Turbo |
| Design Arena: agents building mobile apps | 1134 | 1090 | GLM 5V Turbo |
| Design Arena: agents building Android apps | 1267 | 1176 | GLM 5V Turbo |
| Design Arena: agents building Godot games | 957 | 1142 | GPT-5.2-Codex |
| Design Arena: agents building games | 1102 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: HTML slides | 1070 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: PowerPoint slides | 1127 | Not measured | Only GLM 5V Turbo measured |
| τ²-Bench Telecom | 98.5% | 92.1% | GLM 5V Turbo |
| Neither model has a result on the other 32 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GLM 5V Turbo | GPT-5.2-Codex | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 80.9% | 89.9% | GPT-5.2-Codex |
| Humanity's Last Exam (Artificial Analysis run) | 17.1% | 35.7% | GPT-5.2-Codex |
| LMArena Text: hard prompts | 1443 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: expert | 1453 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: hard prompts in English | 1456 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision: diagrams | 1286 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision: homework | 1273 | Not measured | Only GLM 5V Turbo measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | GLM 5V Turbo | GPT-5.2-Codex | Leader |
|---|---|---|---|
| LMArena Text: math | 1442 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: mathematical work | 1447 | Not measured | Only GLM 5V Turbo measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | GLM 5V Turbo | GPT-5.2-Codex | Leader |
|---|---|---|---|
| LMArena Text: science | 1448 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: medicine and healthcare | 1433 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: legal and government | 1436 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: business and finance | 1435 | Not measured | Only GLM 5V Turbo measured |
| Neither model has a result on the other 14 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GLM 5V Turbo | GPT-5.2-Codex | Leader |
|---|---|---|---|
| Design Arena: websites | 1230 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: UI components | 1210 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: game dev | 1218 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: data viz | 1202 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: 3D | 1208 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: all code categories | 1228 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: SVG | 1151 | Not measured | Only GLM 5V Turbo measured |
| Design Arena: ASCII art | 1117 | Not measured | Only GLM 5V Turbo measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GLM 5V Turbo | GPT-5.2-Codex | Leader |
|---|---|---|---|
| IFBench | 61.1% | 77.6% | GPT-5.2-Codex |
| Long context reasoning (AA-LCR) | 70.3% | 82.3% | GPT-5.2-Codex |
| LMArena Text | 1437 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: instruction following | 1423 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: creative writing | 1417 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision | 1264 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: English | 1454 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: non-English | 1420 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: Chinese | 1491 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: German | 1422 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: Korean | 1397 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: French | 1443 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: Spanish | 1452 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: Russian | 1432 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: Polish | 1432 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: multi-turn | 1431 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: longer queries | 1438 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: writing and language | 1420 | Not measured | Only GLM 5V Turbo measured |
| LMArena Text: entertainment and media | 1407 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision: English | 1274 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision: Chinese | 1329 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision: reading text | 1270 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision: humor | 1268 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision: captioning | 1264 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision: recognizing things | 1241 | Not measured | Only GLM 5V Turbo measured |
| LMArena Vision: creative writing | 1252 | Not measured | Only GLM 5V Turbo measured |
| LMArena Document | 1416 | Not measured | Only GLM 5V Turbo measured |
| Neither model has a result on the other 19 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 5V Turbo | GPT-5.2-Codex | Leader |
|---|---|---|---|
| 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 5V Turbo costs less
Repository review
50K input + 3K output tokens
GLM 5V Turbo costs less
Agent loop
200K input + 10K output tokens
GLM 5V Turbo 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.
| Specification | Z.ai GLM 5V Turbo | OpenAI GPT-5.2-Codex |
|---|---|---|
| Maker | Z.ai | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | April 1, 2026 | January 14, 2026 |
| Context window | 203K | 400K |
| Input $/Mtok | $1.20 | $1.75 |
| Output $/Mtok | $4.00 | $14.00 |
| Coding index | Not benchmarked | 45.4 |
| Independent measurements behind it | 1 | 3 |
| Cost per solved task | Not computable | $0.43 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 5V Turbo better than GPT-5.2-Codex for coding?
Only GPT-5.2-Codex has a coding score, 45.4 on the Vibe Coding Index; GLM 5V Turbo has none, so the two cannot be ranked on coding. Pick GLM 5V Turbo for output tokens 3.5x cheaper ($4.00 vs $14.00 per million) and work measured by LMArena WebDev or LMArena WebDev: React, where it leads.
Which is cheaper, GLM 5V Turbo or GPT-5.2-Codex?
GLM 5V Turbo costs $1.20 per million input tokens and $4.00 per million output tokens; GPT-5.2-Codex costs $1.75 and $14.00. Cost per solved task is known for GPT-5.2-Codex only.
Which has the bigger context window, GLM 5V Turbo or GPT-5.2-Codex?
GPT-5.2-Codex, with 400K tokens against 203K.
How many benchmarks is the GLM 5V Turbo vs GPT-5.2-Codex comparison based on?
15 benchmarks have a result for both models as of October 22, 2026. GLM 5V Turbo's coding index rests on 1 independent benchmark and GPT-5.2-Codex's on 3. Where only one model has a result, the page says so instead of naming a winner.