GLM 5.2 vs GPT-5.3-Codex
GLM 5.2 leads GPT-5.3-Codex on coding, 61.1 to 60.0 on the Vibe Coding Index, and GLM 5.2 costs 3.2x less per output token ($4.40 vs $14.00 per million). Updated October 22, 2026; 30 benchmarks have a result for both.
GLM 5.2 or GPT-5.3-Codex: which to pick
GLM 5.2 and GPT-5.3-Codex are level for coding, 61.1 against 60.0 on the Vibe Coding Index, so price and context decide.
Pick GPT-5.3-Codex for a lower cost per solved task ($0.59 against $0.86) and work measured by LiveCodeBench (Vals AI) or Terminal-Bench Hard (Artificial Analysis run), where it leads. Pick GLM 5.2 for output tokens 3.2x cheaper ($4.40 vs $14.00 per million) and a larger context window (1.05M against 400K tokens).
- Shared results
- 30
- GLM 5.2 only
- 68
- GPT-5.3-Codex only
- 4
- Like-for-like categories
- 6 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
Level: 61.1 against 60.0, inside 2 points.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
GLM 5.2
GLM 5.2 leads, 33.7 against 32.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GLM 5.2 has a AA Agentic Index result, 38.4.
Directional only
Reasoning
GPQA Diamond
No call
Only GLM 5.2 has a GPQA Diamond result, 85.6%.
Directional only
Knowledge
MMLU Pro
No call
Only GLM 5.2 has a MMLU Pro result, 86.7%.
Directional only
Web design
Design Arena: websites
GLM 5.2
GLM 5.2 leads, 1285 against 1162.
Same board, both measured
Long documents
Listed context window
GLM 5.2
GLM 5.2 takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 5.2
GLM 5.2 $0.0036, GPT-5.3-Codex $0.0088 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.3-Codex
GLM 5.2 $0.86, GPT-5.3-Codex $0.59.
Published attempt cost and pass rate
At a glance
- Coding index
- GLM 5.2 61.1 from 4 benchmarks, GPT-5.3-Codex 60.0 from 3 benchmarks.
- Widest category
- Web design, 16.5 points apart on average over 8 shared benchmarks.
- Widest single gap
- Design Arena: 3D: GLM 5.2 1287 against GPT-5.3-Codex 1007, 35.0 points apart on a 0 to 100 scale.
- Output price
- GLM 5.2 $4.40 against GPT-5.3-Codex $14.00 per million output tokens, 3.2x apart.
- Context window
- GLM 5.2 takes 1.05M tokens, GPT-5.3-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 5.2 | Bars | GPT-5.3-Codex | Ties |
|---|---|---|---|---|
| Coding | 5 | 4 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 7 | 0 | ||
| Reasoning | 0 | 2 | ||
| Web design | 8 | 0 | ||
| General | 0 | 2 | ||
| All shared boards | 21 | 9 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index54
| Benchmark | GLM 5.2 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| LMArena WebDev | 1604 | 1407 | GLM 5.2 |
| AA Coding Index | 68.8 | Not measured | Only GLM 5.2 measured |
| LiveCodeBench (Vals AI) | 69.5% | 87.3% | GPT-5.3-Codex |
| SWE-bench Verified (Vals AI) | 82.8% | 78.0% | GLM 5.2 |
| Vibe Code Bench (Vals AI) | 64.0% | 61.8% | GLM 5.2 |
| Code migration (Vals AI) | 37.9% | Not measured | Only GLM 5.2 measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only GLM 5.2 measured |
| IOI (Vals AI) | Not measured | 53.8% | Only GPT-5.3-Codex measured |
| Terminal-Bench 2.1 (Vals AI) | 67.8% | Not measured | Only GLM 5.2 measured |
| SkillsBench (Vals AI) | 45.1% | Not measured | Only GLM 5.2 measured |
| SciCode | 51.2% | Not measured | Only GLM 5.2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 50.8% | 53.0% | GPT-5.3-Codex |
| Terminal-Bench | Not measured | 78.4% | Only GPT-5.3-Codex measured |
| FrontierCode | 24.5% | Not measured | Only GLM 5.2 measured |
| WeirdML | 70.1% | 79.3% | GPT-5.3-Codex |
| ALE-Bench | 1047.0 | 1655.2 | GPT-5.3-Codex |
| LMArena Text: coding | 1487 | Not measured | Only GLM 5.2 measured |
| LMArena Text: software and IT | 1486 | Not measured | Only GLM 5.2 measured |
| LMArena WebDev: React | 1617 | 1395 | GLM 5.2 |
| LMArena WebDev: HTML | 1565 | 1422 | GLM 5.2 |
| LMArena WebDev: from an image | Not measured | 1443 | Only GPT-5.3-Codex measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GLM 5.2 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| AA Intelligence Index | 33.7 | 32.5 | GLM 5.2 |
| Epoch Capabilities Index | 151.9 | 157.1 | GPT-5.3-Codex |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | GLM 5.2 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| AA Agentic Index | 38.4 | Not measured | Only GLM 5.2 measured |
| Design Arena: agents building web apps | 1222 | 1032 | GLM 5.2 |
| Design Arena: agents building full-stack apps | 1241 | 983 | GLM 5.2 |
| Design Arena: agents building mobile apps | 1159 | 1053 | GLM 5.2 |
| Design Arena: agents building Android apps | 1178 | 1084 | GLM 5.2 |
| Design Arena: agents building Godot games | 1142 | 1124 | GLM 5.2 |
| Design Arena: agents building games | 1206 | Not measured | Only GLM 5.2 measured |
| Design Arena: HTML slides | 1125 | Not measured | Only GLM 5.2 measured |
| Design Arena: PowerPoint slides | 1170 | Not measured | Only GLM 5.2 measured |
| SREBench (Vals AI) | 0.0% | Not measured | Only GLM 5.2 measured |
| Finance Agent (Vals AI) | 49.7% | Not measured | Only GLM 5.2 measured |
| Legal Research Bench (Vals AI) | 31.3% | Not measured | Only GLM 5.2 measured |
| Excel Modeling Benchmark (Vals AI) | 61.5% | Not measured | Only GLM 5.2 measured |
| τ²-Bench Telecom | 99.1% | 86.0% | GLM 5.2 |
| APEX-Agents | 45.2% | Not measured | Only GLM 5.2 measured |
| METR time horizons | Not measured | 74.5% | Only GPT-5.3-Codex measured |
| PostTrainBench | 31.7% | Not measured | Only GLM 5.2 measured |
| Vending-Bench 2 | $8,314 | $5,940 | GLM 5.2 |
| Neither model has a result on the other 23 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GLM 5.2 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| GPQA Diamond | 85.6% | Not measured | Only GLM 5.2 measured |
| GPQA Diamond (Artificial Analysis run) | 89.5% | 91.5% | GPT-5.3-Codex |
| Humanity's Last Exam (Artificial Analysis run) | 41.1% | 42.5% | GPT-5.3-Codex |
| GPQA Diamond (Epoch AI run) | 91.9% | Not measured | Only GLM 5.2 measured |
| ARC-AGI | 77.0% | Not measured | Only GLM 5.2 measured |
| ARC-AGI-2 | 22.8% | Not measured | Only GLM 5.2 measured |
| SimpleBench | 58.8% | Not measured | Only GLM 5.2 measured |
| Chess puzzles | 22.0% | Not measured | Only GLM 5.2 measured |
| Mystery game puzzles | 19.0% | Not measured | Only GLM 5.2 measured |
| EBR-bench | 9.5% | Not measured | Only GLM 5.2 measured |
| LMArena Text: hard prompts | 1481 | Not measured | Only GLM 5.2 measured |
| LMArena Text: expert | 1487 | Not measured | Only GLM 5.2 measured |
| LMArena Text: hard prompts in English | 1481 | Not measured | Only GLM 5.2 measured |
| Kagi LLM Benchmark | 62.6% | Not measured | Only GLM 5.2 measured |
| Neither model has a result on the other 8 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GLM 5.2 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| OTIS Mock AIME | 86.4% | Not measured | Only GLM 5.2 measured |
| FrontierMath, tiers 1 to 3 | 59.2% | Not measured | Only GLM 5.2 measured |
| FrontierMath, tier 4 | 29.3% | Not measured | Only GLM 5.2 measured |
| ProofBench | 35.0% | Not measured | Only GLM 5.2 measured |
| LMArena Text: math | 1483 | Not measured | Only GLM 5.2 measured |
| LMArena Text: mathematical work | 1489 | Not measured | Only GLM 5.2 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | GLM 5.2 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| MMLU Pro | 86.7% | Not measured | Only GLM 5.2 measured |
| LegalBench (Vals AI) | 84.1% | Not measured | Only GLM 5.2 measured |
| CorpFin (Vals AI) | 66.1% | Not measured | Only GLM 5.2 measured |
| TaxEval (Vals AI) | 73.3% | Not measured | Only GLM 5.2 measured |
| MedCode (Vals AI) | 40.8% | Not measured | Only GLM 5.2 measured |
| SimpleQA Verified | 34.2% | Not measured | Only GLM 5.2 measured |
| LMArena Text: science | 1489 | Not measured | Only GLM 5.2 measured |
| LMArena Text: medicine and healthcare | 1475 | Not measured | Only GLM 5.2 measured |
| LMArena Text: legal and government | 1486 | Not measured | Only GLM 5.2 measured |
| LMArena Text: business and finance | 1451 | Not measured | Only GLM 5.2 measured |
| Neither model has a result on the other 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | GLM 5.2 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| Design Arena: websites | 1285 | 1162 | GLM 5.2 |
| Design Arena: UI components | 1294 | 1134 | GLM 5.2 |
| Design Arena: game dev | 1268 | 1161 | GLM 5.2 |
| Design Arena: data viz | 1285 | 1164 | GLM 5.2 |
| Design Arena: 3D | 1287 | 1007 | GLM 5.2 |
| Design Arena: all code categories | 1287 | 1144 | GLM 5.2 |
| Design Arena: SVG | 1213 | 1129 | GLM 5.2 |
| Design Arena: ASCII art | 1191 | 1152 | GLM 5.2 |
| 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 5.2 | GPT-5.3-Codex | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | 83.5% | Not measured | Only GLM 5.2 measured |
| IFBench | 73.3% | 75.4% | GPT-5.3-Codex |
| Long context reasoning (AA-LCR) | 78.3% | 83.3% | GPT-5.3-Codex |
| DTBench | 93.6% | Not measured | Only GLM 5.2 measured |
| LMCA | 45.8% | Not measured | Only GLM 5.2 measured |
| Surface Evolver Bench | 55.6% | Not measured | Only GLM 5.2 measured |
| LMArena Text | 1470 | Not measured | Only GLM 5.2 measured |
| LMArena Text: instruction following | 1466 | Not measured | Only GLM 5.2 measured |
| LMArena Text: creative writing | 1463 | Not measured | Only GLM 5.2 measured |
| LMArena Text: English | 1475 | Not measured | Only GLM 5.2 measured |
| LMArena Text: non-English | 1459 | Not measured | Only GLM 5.2 measured |
| LMArena Text: Chinese | 1522 | Not measured | Only GLM 5.2 measured |
| LMArena Text: German | 1470 | Not measured | Only GLM 5.2 measured |
| LMArena Text: Japanese | 1450 | Not measured | Only GLM 5.2 measured |
| LMArena Text: Korean | 1440 | Not measured | Only GLM 5.2 measured |
| LMArena Text: French | 1479 | Not measured | Only GLM 5.2 measured |
| LMArena Text: Spanish | 1478 | Not measured | Only GLM 5.2 measured |
| LMArena Text: Russian | 1468 | Not measured | Only GLM 5.2 measured |
| LMArena Text: Polish | 1456 | Not measured | Only GLM 5.2 measured |
| LMArena Text: multi-turn | 1469 | Not measured | Only GLM 5.2 measured |
| LMArena Text: longer queries | 1480 | Not measured | Only GLM 5.2 measured |
| LMArena Text: writing and language | 1463 | Not measured | Only GLM 5.2 measured |
| LMArena Text: entertainment and media | 1450 | Not measured | Only GLM 5.2 measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 5.2 | GPT-5.3-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 5.2 costs less
Repository review
50K input + 3K output tokens
GLM 5.2 costs less
Agent loop
200K input + 10K output tokens
GLM 5.2 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 5.2 | OpenAI GPT-5.3-Codex |
|---|---|---|
| Maker | Z.ai | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | June 16, 2026 | February 24, 2026 |
| Context window | 1.05M | 400K |
| Input $/Mtok | $1.40 | $1.75 |
| Output $/Mtok | $4.40 | $14.00 |
| Coding index | 61.1 | 60.0 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | $0.86 | $0.59 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 5.2 better than GPT-5.3-Codex for coding?
GLM 5.2 and GPT-5.3-Codex are level for coding, 61.1 against 60.0 on the Vibe Coding Index, so price and context decide. Pick GPT-5.3-Codex for a lower cost per solved task ($0.59 against $0.86) and work measured by LiveCodeBench (Vals AI) or Terminal-Bench Hard (Artificial Analysis run), where it leads. Pick GLM 5.2 for output tokens 3.2x cheaper ($4.40 vs $14.00 per million) and a larger context window (1.05M against 400K tokens).
Which is cheaper, GLM 5.2 or GPT-5.3-Codex?
GLM 5.2 costs $1.40 per million input tokens and $4.40 per million output tokens; GPT-5.3-Codex costs $1.75 and $14.00. Per solved SWE-bench Verified task, GLM 5.2 costs $0.86 and GPT-5.3-Codex $0.59.
Which has the bigger context window, GLM 5.2 or GPT-5.3-Codex?
GLM 5.2, with 1.05M tokens against 400K.
How many benchmarks is the GLM 5.2 vs GPT-5.3-Codex comparison based on?
30 benchmarks have a result for both models as of October 22, 2026. GLM 5.2's coding index rests on 4 independent benchmarks and GPT-5.3-Codex's on 3. Where only one model has a result, the page says so instead of naming a winner.