GLM 4.5 Air vs GLM 4.7 Flash
GLM 4.7 Flash leads GLM 4.5 Air on the Artificial Analysis Intelligence Index, 14.9 to 11.1, and GLM 4.7 Flash costs 2.8x less per output token ($0.40 vs $1.10 per million). Updated October 21, 2026; 41 benchmarks have a result for both.
GLM 4.5 Air or GLM 4.7 Flash: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GLM 4.5 Air for work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 41
- GLM 4.5 Air only
- 7
- GLM 4.7 Flash only
- 2
- 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
GLM 4.7 Flash
GLM 4.7 Flash leads, 14.9 against 11.1.
Same board, both measured
Web design
Design Arena: websites
GLM 4.7 Flash
GLM 4.7 Flash leads, 1194 against 1146.
Same board, both measured
Long documents
Listed context window
GLM 4.7 Flash
GLM 4.7 Flash takes 200K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 4.7 Flash
GLM 4.5 Air $0.0008, GLM 4.7 Flash $0.0003 per turn.
List prices
At a glance
- Coding index
- GLM 4.5 Air not benchmarked, GLM 4.7 Flash not benchmarked.
- Widest category
- Agentic work, 52.3 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: GLM 4.5 Air 46.5% against GLM 4.7 Flash 98.8%, 52.3 points apart on a 0 to 100 scale.
- Output price
- GLM 4.5 Air $1.10 against GLM 4.7 Flash $0.40 per million output tokens, 2.8x apart.
- Context window
- GLM 4.5 Air takes 131K tokens, GLM 4.7 Flash 200K.
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 | GLM 4.7 Flash | Ties |
|---|---|---|---|---|
| Coding | 2 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 4 | 1 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 0 | ||
| Web design | 3 | 4 | ||
| General | 17 | 1 | ||
| All shared boards | 32 | 9 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
| Benchmark | GLM 4.5 Air | GLM 4.7 Flash | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 68.4% | Not measured | Only GLM 4.5 Air measured |
| Terminal-Bench Hard (Artificial Analysis run) | 20.5% | 22.0% | GLM 4.7 Flash |
| GSO-Bench | 2.9% | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: coding | 1397 | 1382 | GLM 4.5 Air |
| LMArena Text: software and IT | 1401 | 1389 | GLM 4.5 Air |
| Neither model has a result on the other 34 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 4.5 Air | GLM 4.7 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.1 | 14.9 | GLM 4.7 Flash |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 4.5 Air | GLM 4.7 Flash | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 46.5% | 98.8% | GLM 4.7 Flash |
| Neither model has a result on the other 40 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | GLM 4.5 Air | GLM 4.7 Flash | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 73.3% | 58.1% | GLM 4.5 Air |
| Humanity's Last Exam (Artificial Analysis run) | 7.0% | 7.6% | GLM 4.7 Flash |
| GPQA Diamond (Epoch AI run) | Not measured | 60.5% | Only GLM 4.7 Flash measured |
| LMArena Text: hard prompts | 1379 | 1356 | GLM 4.5 Air |
| LMArena Text: expert | 1370 | 1357 | GLM 4.5 Air |
| LMArena Text: hard prompts in English | 1388 | 1369 | 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 | GLM 4.7 Flash | 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 |
| OTIS Mock AIME | Not measured | 58.3% | Only GLM 4.7 Flash measured |
| LMArena Text: math | 1396 | 1355 | GLM 4.5 Air |
| LMArena Text: mathematical work | 1396 | 1369 | 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 index40
| Benchmark | GLM 4.5 Air | GLM 4.7 Flash | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 81.5% | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: science | 1407 | 1358 | GLM 4.5 Air |
| LMArena Text: medicine and healthcare | 1402 | 1343 | GLM 4.5 Air |
| LMArena Text: legal and government | 1382 | 1357 | 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 index34
| Benchmark | GLM 4.5 Air | GLM 4.7 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1146 | 1194 | GLM 4.7 Flash |
| Design Arena: UI components | 1123 | 1208 | GLM 4.7 Flash |
| Design Arena: game dev | 1094 | 1135 | GLM 4.7 Flash |
| Design Arena: data viz | 1186 | 1123 | GLM 4.5 Air |
| Design Arena: 3D | 1123 | 1121 | GLM 4.5 Air |
| Design Arena: all code categories | 1137 | 1178 | GLM 4.7 Flash |
| Design Arena: SVG | 1071 | 1038 | GLM 4.5 Air |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index171
| Benchmark | GLM 4.5 Air | GLM 4.7 Flash | Leader |
|---|---|---|---|
| IFBench | 37.6% | 60.8% | GLM 4.7 Flash |
| Long context reasoning (AA-LCR) | 46.7% | 41.7% | GLM 4.5 Air |
| LMArena Text | 1384 | 1351 | GLM 4.5 Air |
| LMArena Text: instruction following | 1354 | 1327 | GLM 4.5 Air |
| LMArena Text: creative writing | 1343 | 1296 | GLM 4.5 Air |
| LMArena Text: English | 1397 | 1373 | GLM 4.5 Air |
| LMArena Text: non-English | 1366 | 1330 | GLM 4.5 Air |
| LMArena Text: Chinese | 1426 | 1403 | GLM 4.5 Air |
| LMArena Text: German | 1377 | 1336 | GLM 4.5 Air |
| LMArena Text: Japanese | 1348 | Not measured | Only GLM 4.5 Air measured |
| LMArena Text: Korean | 1308 | 1283 | GLM 4.5 Air |
| LMArena Text: French | 1400 | 1332 | GLM 4.5 Air |
| LMArena Text: Spanish | 1385 | 1350 | GLM 4.5 Air |
| LMArena Text: Russian | 1373 | 1333 | GLM 4.5 Air |
| LMArena Text: Polish | 1368 | 1291 | GLM 4.5 Air |
| LMArena Text: multi-turn | 1371 | 1342 | GLM 4.5 Air |
| LMArena Text: longer queries | 1366 | 1345 | GLM 4.5 Air |
| LMArena Text: writing and language | 1354 | 1320 | GLM 4.5 Air |
| LMArena Text: entertainment and media | 1339 | 1304 | 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 | GLM 4.7 Flash | 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 4.7 Flash costs less
Repository review
50K input + 3K output tokens
GLM 4.7 Flash costs less
Agent loop
200K input + 10K output tokens
GLM 4.7 Flash 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 | Z.ai GLM 4.7 Flash |
|---|---|---|
| Maker | Z.ai | Z.ai |
| Weights | Open weights | Open weights |
| Released | July 25, 2025 | January 19, 2026 |
| Context window | 131K | 200K |
| Input $/Mtok | $0.20 | $0.0653 |
| Output $/Mtok | $1.10 | $0.40 |
| 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 GLM 4.7 Flash for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GLM 4.5 Air for work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, GLM 4.5 Air or GLM 4.7 Flash?
GLM 4.5 Air costs $0.20 per million input tokens and $1.10 per million output tokens; GLM 4.7 Flash costs $0.0653 and $0.40. Cost per solved task is known for neither of them.
Which has the bigger context window, GLM 4.5 Air or GLM 4.7 Flash?
GLM 4.7 Flash, with 200K tokens against 131K.
How many benchmarks is the GLM 4.5 Air vs GLM 4.7 Flash comparison based on?
41 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 GLM 4.7 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.