GLM 4.5 Air vs Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B leads GLM 4.5 Air on the Artificial Analysis Intelligence Index, 11.9 to 11.1, and GLM 4.5 Air costs 1.4x less per output token ($1.10 vs $1.50 per million). Updated October 21, 2026; 46 benchmarks have a result for both.
GLM 4.5 Air or Qwen3 Coder 480B A35B: 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 1.4x cheaper ($1.10 vs $1.50 per million) and work measured by GSO-Bench or LMArena Text: coding, where it leads.
- Shared results
- 46
- GLM 4.5 Air only
- 2
- Qwen3 Coder 480B A35B only
- 7
- Like-for-like categories
- 8 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
Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B leads, 11.9 against 11.1.
Same board, both measured
Web design
Design Arena: websites
Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B leads, 1159 against 1146.
Same board, both measured
Long documents
Listed context window
Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 4.5 Air
GLM 4.5 Air $0.0008, Qwen3 Coder 480B A35B $0.0010 per turn.
List prices
At a glance
- Coding index
- GLM 4.5 Air not benchmarked, Qwen3 Coder 480B A35B not benchmarked.
- Widest category
- Math, 23.2 points apart on average over 4 shared benchmarks.
- Widest single gap
- AA Math Index: GLM 4.5 Air 80.7 against Qwen3 Coder 480B A35B 39.3, 41.4 points apart on a 0 to 100 scale.
- Output price
- GLM 4.5 Air $1.10 against Qwen3 Coder 480B A35B $1.50 per million output tokens, 1.4x apart.
- Context window
- GLM 4.5 Air takes 131K tokens, Qwen3 Coder 480B A35B 262K.
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 | Qwen3 Coder 480B A35B | Ties |
|---|---|---|---|---|
| Coding | 3 | 2 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 5 | 1 | ||
| Math | 4 | 0 | ||
| Knowledge | 5 | 0 | ||
| Web design | 2 | 3 | ||
| General | 16 | 3 | ||
| All shared boards | 36 | 10 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index32
| Benchmark | GLM 4.5 Air | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 69.6% | Only Qwen3 Coder 480B A35B measured |
| LMArena WebDev | Not measured | 1275 | Only Qwen3 Coder 480B A35B measured |
| LiveCodeBench (Artificial Analysis run) | 68.4% | 58.5% | GLM 4.5 Air |
| Terminal-Bench Hard (Artificial Analysis run) | 20.5% | 18.9% | GLM 4.5 Air |
| Terminal-Bench | Not measured | 27.2% | Only Qwen3 Coder 480B A35B measured |
| GSO-Bench | 2.9% | 4.9% | Qwen3 Coder 480B A35B |
| WeirdML | Not measured | 41.2% | Only Qwen3 Coder 480B A35B measured |
| ALE-Bench | Not measured | 461.4 | Only Qwen3 Coder 480B A35B measured |
| LMArena Text: coding | 1397 | 1412 | Qwen3 Coder 480B A35B |
| LMArena Text: software and IT | 1401 | 1393 | GLM 4.5 Air |
| LMArena WebDev: React | Not measured | 1257 | Only Qwen3 Coder 480B A35B measured |
| LMArena WebDev: HTML | Not measured | 1287 | Only Qwen3 Coder 480B A35B measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 4.5 Air | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.1 | 11.9 | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 4.5 Air | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 46.5% | 43.6% | GLM 4.5 Air |
| Neither model has a result on the other 40 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | GLM 4.5 Air | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 73.3% | 61.8% | GLM 4.5 Air |
| Humanity's Last Exam (Artificial Analysis run) | 7.0% | 4.5% | GLM 4.5 Air |
| LMArena Text: hard prompts | 1379 | 1372 | GLM 4.5 Air |
| LMArena Text: expert | 1370 | 1338 | GLM 4.5 Air |
| LMArena Text: hard prompts in English | 1388 | 1380 | GLM 4.5 Air |
| Kagi LLM Benchmark | 43.0% | 49.5% | Qwen3 Coder 480B A35B |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | GLM 4.5 Air | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| AA Math Index | 80.7 | 39.3 | GLM 4.5 Air |
| AIME 2025 (Artificial Analysis run) | 80.7% | 39.3% | GLM 4.5 Air |
| LMArena Text: math | 1396 | 1365 | GLM 4.5 Air |
| LMArena Text: mathematical work | 1396 | 1367 | GLM 4.5 Air |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GLM 4.5 Air | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 81.5% | 78.8% | GLM 4.5 Air |
| LMArena Text: science | 1407 | 1347 | GLM 4.5 Air |
| LMArena Text: medicine and healthcare | 1402 | 1347 | GLM 4.5 Air |
| LMArena Text: legal and government | 1382 | 1358 | GLM 4.5 Air |
| LMArena Text: business and finance | 1371 | 1343 | GLM 4.5 Air |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index23
| Benchmark | GLM 4.5 Air | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| Design Arena: websites | 1146 | 1159 | Qwen3 Coder 480B A35B |
| Design Arena: UI components | 1123 | 1113 | GLM 4.5 Air |
| Design Arena: game dev | 1094 | 1099 | Qwen3 Coder 480B A35B |
| Design Arena: data viz | 1186 | 1084 | GLM 4.5 Air |
| Design Arena: 3D | 1123 | Not measured | Only GLM 4.5 Air measured |
| Design Arena: all code categories | 1137 | 1143 | Qwen3 Coder 480B A35B |
| 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 index163
| Benchmark | GLM 4.5 Air | Qwen3 Coder 480B A35B | Leader |
|---|---|---|---|
| IFBench | 37.6% | 40.5% | Qwen3 Coder 480B A35B |
| Long context reasoning (AA-LCR) | 46.7% | 45.7% | GLM 4.5 Air |
| LMArena Text | 1384 | 1357 | GLM 4.5 Air |
| LMArena Text: instruction following | 1354 | 1355 | Qwen3 Coder 480B A35B |
| LMArena Text: creative writing | 1343 | 1333 | GLM 4.5 Air |
| LMArena Text: English | 1397 | 1359 | GLM 4.5 Air |
| LMArena Text: non-English | 1366 | 1346 | GLM 4.5 Air |
| LMArena Text: Chinese | 1426 | 1357 | GLM 4.5 Air |
| LMArena Text: German | 1377 | 1325 | GLM 4.5 Air |
| LMArena Text: Japanese | 1348 | 1311 | GLM 4.5 Air |
| LMArena Text: Korean | 1308 | 1305 | GLM 4.5 Air |
| LMArena Text: French | 1400 | 1398 | GLM 4.5 Air |
| LMArena Text: Spanish | 1385 | 1360 | GLM 4.5 Air |
| LMArena Text: Russian | 1373 | 1366 | GLM 4.5 Air |
| LMArena Text: Polish | 1368 | 1344 | GLM 4.5 Air |
| LMArena Text: multi-turn | 1371 | 1366 | GLM 4.5 Air |
| LMArena Text: longer queries | 1366 | 1378 | Qwen3 Coder 480B A35B |
| LMArena Text: writing and language | 1354 | 1340 | GLM 4.5 Air |
| LMArena Text: entertainment and media | 1339 | 1317 | GLM 4.5 Air |
| Neither model has a result on the other 27 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 4.5 Air | Qwen3 Coder 480B A35B | 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 | Qwen3 Coder 480B A35B |
|---|---|---|
| Maker | Z.ai | Qwen |
| Weights | Open weights | Open weights |
| Released | July 25, 2025 | July 23, 2025 |
| Context window | 131K | 262K |
| Input $/Mtok | $0.20 | $0.30 |
| Output $/Mtok | $1.10 | $1.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.5 Air better than Qwen3 Coder 480B A35B 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 1.4x cheaper ($1.10 vs $1.50 per million) and work measured by GSO-Bench or LMArena Text: coding, where it leads.
Which is cheaper, GLM 4.5 Air or Qwen3 Coder 480B A35B?
GLM 4.5 Air costs $0.20 per million input tokens and $1.10 per million output tokens; Qwen3 Coder 480B A35B costs $0.30 and $1.50. Cost per solved task is known for neither of them.
Which has the bigger context window, GLM 4.5 Air or Qwen3 Coder 480B A35B?
Qwen3 Coder 480B A35B, with 262K tokens against 131K.
How many benchmarks is the GLM 4.5 Air vs Qwen3 Coder 480B A35B comparison based on?
46 benchmarks have a result for both models as of October 21, 2026. GLM 4.5 Air's coding index rests on 0 independent benchmarks and Qwen3 Coder 480B A35B's on 1. Where only one model has a result, the page says so instead of naming a winner.