GLM 4.6V vs GLM 4.7 Flash
Updated October 21, 2026. 27 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
GLM 4.6V has the edge where what matters is Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 27
- GLM 4.6V only
- 11
- GLM 4.7 Flash only
- 16
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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 11.2.
Same board, both measured
Web design
Design Arena: websites
No call
Only GLM 4.7 Flash has a Design Arena: websites result, 1194.
Directional only
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 4.6V $0.0008, GLM 4.7 Flash $0.0003 per turn.
List prices
At a glance
- Coding index
- GLM 4.6V not benchmarked, GLM 4.7 Flash not benchmarked.
- Widest category
- Agentic work, 67.3 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: GLM 4.6V 31.6% against GLM 4.7 Flash 98.8%, 67.3 points apart on a 0 to 100 scale.
- Output price
- GLM 4.6V $0.90 against GLM 4.7 Flash $0.40 per million output tokens, 2.3x apart.
- Context window
- GLM 4.6V 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 4.6V | Bars | GLM 4.7 Flash | Ties |
|---|---|---|---|---|
| Coding | 2 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 5 | 0 | ||
| Knowledge | 4 | 0 | ||
| General | 12 | 1 | ||
| All shared boards | 23 | 4 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
| Benchmark | GLM 4.6V | GLM 4.7 Flash | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | 41.1% | Not measured | Only GLM 4.6V measured |
| Terminal-Bench Hard (Artificial Analysis run) | 14.4% | 22.0% | GLM 4.7 Flash |
| LMArena Text: coding | 1389 | 1382 | GLM 4.6V |
| LMArena Text: software and IT | 1391 | 1389 | GLM 4.6V |
| 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 4.6V | GLM 4.7 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.2 | 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 4.6V | GLM 4.7 Flash | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 31.6% | 98.8% | GLM 4.7 Flash |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GLM 4.6V | GLM 4.7 Flash | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 71.9% | 58.1% | GLM 4.6V |
| Humanity's Last Exam (Artificial Analysis run) | 9.6% | 7.6% | GLM 4.6V |
| GPQA Diamond (Epoch AI run) | Not measured | 60.5% | Only GLM 4.7 Flash measured |
| LMArena Text: hard prompts | 1367 | 1356 | GLM 4.6V |
| LMArena Text: expert | 1371 | 1357 | GLM 4.6V |
| LMArena Text: hard prompts in English | 1391 | 1369 | GLM 4.6V |
| LMArena Vision: diagrams | 1182 | Not measured | Only GLM 4.6V measured |
| LMArena Vision: homework | 1155 | Not measured | Only GLM 4.6V measured |
| Neither model has a result on the other 13 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | GLM 4.6V | GLM 4.7 Flash | Leader |
|---|---|---|---|
| AA Math Index | 85.3 | Not measured | Only GLM 4.6V measured |
| AIME 2025 (Artificial Analysis run) | 85.3% | Not measured | Only GLM 4.6V measured |
| OTIS Mock AIME | Not measured | 58.3% | Only GLM 4.7 Flash measured |
| LMArena Text: math | Not measured | 1355 | Only GLM 4.7 Flash measured |
| LMArena Text: mathematical work | Not measured | 1369 | Only GLM 4.7 Flash measured |
| 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 4.6V | GLM 4.7 Flash | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 79.9% | Not measured | Only GLM 4.6V measured |
| LMArena Text: science | 1389 | 1358 | GLM 4.6V |
| LMArena Text: medicine and healthcare | 1389 | 1343 | GLM 4.6V |
| LMArena Text: legal and government | 1393 | 1357 | GLM 4.6V |
| LMArena Text: business and finance | 1359 | 1343 | GLM 4.6V |
| Neither model has a result on the other 12 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | GLM 4.6V | GLM 4.7 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1194 | Only GLM 4.7 Flash measured |
| Design Arena: UI components | Not measured | 1208 | Only GLM 4.7 Flash measured |
| Design Arena: game dev | Not measured | 1135 | Only GLM 4.7 Flash measured |
| Design Arena: data viz | Not measured | 1123 | Only GLM 4.7 Flash measured |
| Design Arena: 3D | Not measured | 1121 | Only GLM 4.7 Flash measured |
| Design Arena: all code categories | Not measured | 1178 | Only GLM 4.7 Flash measured |
| Design Arena: SVG | Not measured | 1038 | Only GLM 4.7 Flash measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index121
| Benchmark | GLM 4.6V | GLM 4.7 Flash | Leader |
|---|---|---|---|
| IFBench | 30.1% | 60.8% | GLM 4.7 Flash |
| Long context reasoning (AA-LCR) | 48.7% | 41.7% | GLM 4.6V |
| LMArena Text | 1376 | 1351 | GLM 4.6V |
| LMArena Text: instruction following | 1350 | 1327 | GLM 4.6V |
| LMArena Text: creative writing | 1347 | 1296 | GLM 4.6V |
| LMArena Vision | 1164 | Not measured | Only GLM 4.6V measured |
| LMArena Text: English | 1395 | 1373 | GLM 4.6V |
| LMArena Text: non-English | 1358 | 1330 | GLM 4.6V |
| LMArena Text: Chinese | 1425 | 1403 | GLM 4.6V |
| LMArena Text: German | Not measured | 1336 | Only GLM 4.7 Flash measured |
| LMArena Text: Korean | Not measured | 1283 | Only GLM 4.7 Flash measured |
| LMArena Text: French | Not measured | 1332 | Only GLM 4.7 Flash measured |
| LMArena Text: Spanish | Not measured | 1350 | Only GLM 4.7 Flash measured |
| LMArena Text: Russian | 1339 | 1333 | GLM 4.6V |
| LMArena Text: Polish | Not measured | 1291 | Only GLM 4.7 Flash measured |
| LMArena Text: multi-turn | 1359 | 1342 | GLM 4.6V |
| LMArena Text: longer queries | 1357 | 1345 | GLM 4.6V |
| LMArena Text: writing and language | 1347 | 1320 | GLM 4.6V |
| LMArena Text: entertainment and media | 1343 | 1304 | GLM 4.6V |
| LMArena Vision: English | 1179 | Not measured | Only GLM 4.6V measured |
| LMArena Vision: Chinese | 1217 | Not measured | Only GLM 4.6V measured |
| LMArena Vision: reading text | 1171 | Not measured | Only GLM 4.6V measured |
| LMArena Vision: creative writing | 1113 | Not measured | Only GLM 4.6V 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 4.6V | 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 4.6V | Z.ai GLM 4.7 Flash |
|---|---|---|
| Maker | Z.ai | Z.ai |
| Weights | Open weights | Open weights |
| Released | December 8, 2025 | January 19, 2026 |
| Context window | 131K | 200K |
| Input $/Mtok | $0.30 | $0.0653 |
| Output $/Mtok | $0.90 | $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 4.6V better than GLM 4.7 Flash for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. GLM 4.6V has the edge where what matters is Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, GLM 4.6V or GLM 4.7 Flash?
GLM 4.6V costs $0.30 per million input tokens and $0.90 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 4.6V or GLM 4.7 Flash?
GLM 4.7 Flash, with 200K tokens against 131K.
How many benchmarks is the GLM 4.6V vs GLM 4.7 Flash comparison based on?
27 benchmarks have a result for both models as of October 21, 2026. GLM 4.6V'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.