GLM 4.5 Air vs GPT-4
GLM 4.5 Air leads GPT-4 on the Artificial Analysis Intelligence Index, 11.1 to 6.7, and GLM 4.5 Air costs 54.5x less per output token ($1.10 vs $60.00 per million). Updated October 22, 2026; 32 benchmarks have a result for both.
GLM 4.5 Air or GPT-4: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GLM 4.5 Air for output tokens 54.5x cheaper ($1.10 vs $60.00 per million) and a larger context window (131K against 8K tokens).
- Shared results
- 32
- GLM 4.5 Air only
- 16
- GPT-4 only
- 13
- 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
GLM 4.5 Air
GLM 4.5 Air leads, 11.1 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only GLM 4.5 Air has a Design Arena: websites result, 1146.
Directional only
Long documents
Listed context window
GLM 4.5 Air
GLM 4.5 Air takes 131K tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 4.5 Air
GLM 4.5 Air $0.0008, GPT-4 $0.060 per turn.
List prices
At a glance
- Coding index
- GLM 4.5 Air not benchmarked, GPT-4 not benchmarked.
- Widest category
- Knowledge, 35.1 points apart on average over 5 shared benchmarks.
- Widest single gap
- LMArena Text: medicine and healthcare: GLM 4.5 Air 1402 against GPT-4 1145, 42.7 points apart on a 0 to 100 scale.
- Output price
- GLM 4.5 Air $1.10 against GPT-4 $60.00 per million output tokens, 54.5x apart.
- Context window
- GLM 4.5 Air takes 131K tokens, GPT-4 8K.
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 4.5 Air | Bars | GPT-4 | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 4 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 5 | 0 | ||
| General | 18 | 0 | ||
| All shared boards | 32 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | GLM 4.5 Air | GPT-4 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 22.4% | Only GPT-4 measured |
| SWE-bench Lite | Not measured | 39.7% | Only GPT-4 measured |
| SWE-bench (full test set) | Not measured | 12.5% | Only GPT-4 measured |
| AA Coding Index | Not measured | 13.1 | Only GPT-4 measured |
| LiveCodeBench (Artificial Analysis run) | 68.4% | Not measured | Only GLM 4.5 Air measured |
| Terminal-Bench Hard (Artificial Analysis run) | 20.5% | Not measured | Only GLM 4.5 Air measured |
| GSO-Bench | 2.9% | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: coding | 1397 | 1209 | GLM 4.5 Air |
| LMArena Text: software and IT | 1401 | 1195 | GLM 4.5 Air |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 4.5 Air | GPT-4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.1 | 6.7 | GLM 4.5 Air |
| Epoch Capabilities Index | Not measured | 125.7 | Only GPT-4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | GLM 4.5 Air | GPT-4 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 46.5% | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 40 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | GLM 4.5 Air | GPT-4 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 73.3% | 34.9% | GLM 4.5 Air |
| Humanity's Last Exam (Artificial Analysis run) | 7.0% | Not measured | Only GLM 4.5 Air measured |
| BIG-Bench Hard | Not measured | 75.1% | Only GPT-4 measured |
| LMArena Text: hard prompts | 1379 | 1200 | GLM 4.5 Air |
| LMArena Text: expert | 1370 | 1149 | GLM 4.5 Air |
| LMArena Text: hard prompts in English | 1388 | 1209 | GLM 4.5 Air |
| Kagi LLM Benchmark | 43.0% | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GLM 4.5 Air | GPT-4 | Leader |
|---|---|---|---|
| AA Math Index | 80.7 | Not measured | Only GLM 4.5 Air measured |
| AIME 2025 (Artificial Analysis run) | 80.7% | Not measured | Only GLM 4.5 Air measured |
| GSM8K | Not measured | 92.0% | Only GPT-4 measured |
| LMArena Text: math | 1396 | 1230 | GLM 4.5 Air |
| LMArena Text: mathematical work | 1396 | 1228 | GLM 4.5 Air |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GLM 4.5 Air | GPT-4 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 81.5% | 56.2% | GLM 4.5 Air |
| MMLU | Not measured | 86.4% | Only GPT-4 measured |
| AI2 Reasoning Challenge | Not measured | 96.3% | Only GPT-4 measured |
| LMArena Text: science | 1407 | 1177 | GLM 4.5 Air |
| LMArena Text: medicine and healthcare | 1402 | 1145 | GLM 4.5 Air |
| LMArena Text: legal and government | 1382 | 1191 | GLM 4.5 Air |
| LMArena Text: business and finance | 1371 | 1145 | GLM 4.5 Air |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | GLM 4.5 Air | GPT-4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1146 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: UI components | 1120 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: game dev | 1094 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: data viz | 1186 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: 3D | 1122 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: all code categories | 1137 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: SVG | 1071 | Not measured | Only GLM 4.5 Air measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index180
| Benchmark | GLM 4.5 Air | GPT-4 | Leader |
|---|---|---|---|
| IFBench | 37.6% | 33.2% | GLM 4.5 Air |
| Long context reasoning (AA-LCR) | 46.7% | Not measured | Only GLM 4.5 Air measured |
| DTBench | Not measured | 62.7% | Only GPT-4 measured |
| LMCA | Not measured | 17.1% | Only GPT-4 measured |
| HellaSwag | Not measured | 95.3% | Only GPT-4 measured |
| WinoGrande | Not measured | 87.5% | Only GPT-4 measured |
| LMArena Text | 1384 | 1206 | GLM 4.5 Air |
| LMArena Text: instruction following | 1354 | 1201 | GLM 4.5 Air |
| LMArena Text: creative writing | 1343 | 1191 | GLM 4.5 Air |
| LMArena Text: English | 1397 | 1220 | GLM 4.5 Air |
| LMArena Text: non-English | 1366 | 1194 | GLM 4.5 Air |
| LMArena Text: Chinese | 1426 | 1184 | GLM 4.5 Air |
| LMArena Text: German | 1377 | 1198 | GLM 4.5 Air |
| LMArena Text: Japanese | 1348 | 1137 | GLM 4.5 Air |
| LMArena Text: Korean | 1308 | 1087 | GLM 4.5 Air |
| LMArena Text: French | 1400 | 1220 | GLM 4.5 Air |
| LMArena Text: Spanish | 1385 | 1197 | GLM 4.5 Air |
| LMArena Text: Russian | 1373 | 1195 | GLM 4.5 Air |
| LMArena Text: Polish | 1368 | 1265 | GLM 4.5 Air |
| LMArena Text: multi-turn | 1371 | 1206 | GLM 4.5 Air |
| LMArena Text: longer queries | 1366 | 1190 | GLM 4.5 Air |
| LMArena Text: writing and language | 1354 | 1219 | GLM 4.5 Air |
| LMArena Text: entertainment and media | 1339 | 1184 | GLM 4.5 Air |
| 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 4.5 Air | GPT-4 | 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 4.5 Air costs less
Repository review
50K input + 3K output tokens
GLM 4.5 Air costs less
Agent loop
200K input + 10K output tokens
GLM 4.5 Air 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 4.5 Air | OpenAI GPT-4 |
|---|---|---|
| Maker | Z.ai | OpenAI |
| Weights | Open weights | No public weights listed |
| Released | July 25, 2025 | May 28, 2023 |
| Context window | 131K | 8K |
| Input $/Mtok | $0.20 | $30.00 |
| Output $/Mtok | $1.10 | $60.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.5 Air better than GPT-4 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GLM 4.5 Air for output tokens 54.5x cheaper ($1.10 vs $60.00 per million) and a larger context window (131K against 8K tokens).
Which is cheaper, GLM 4.5 Air or GPT-4?
GLM 4.5 Air costs $0.20 per million input tokens and $1.10 per million output tokens; GPT-4 costs $30.00 and $60.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GLM 4.5 Air or GPT-4?
GLM 4.5 Air, with 131K tokens against 8K.
How many benchmarks is the GLM 4.5 Air vs GPT-4 comparison based on?
32 benchmarks have a result for both models as of October 22, 2026. GLM 4.5 Air's coding index rests on 0 independent benchmarks and GPT-4's on 0. Where only one model has a result, the page says so instead of naming a winner.