GLM 4.7 Flash vs Qwen3.6 27B
Qwen3.6 27B leads GLM 4.7 Flash on the Artificial Analysis Intelligence Index, 21.4 to 14.9, and GLM 4.7 Flash costs 6.8x less per output token ($0.40 vs $2.70 per million). Updated October 22, 2026; 9 benchmarks have a result for both.
GLM 4.7 Flash or Qwen3.6 27B: which to pick
Only Qwen3.6 27B has a coding score, 36.8 on the Vibe Coding Index; GLM 4.7 Flash has none, so the two cannot be ranked on coding.
Pick GLM 4.7 Flash for output tokens 6.8x cheaper ($0.40 vs $2.70 per million) and work measured by τ²-Bench Telecom, where it leads.
- Shared results
- 9
- GLM 4.7 Flash only
- 34
- Qwen3.6 27B only
- 15
- 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
Only Qwen3.6 27B has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Qwen3.6 27B
Qwen3.6 27B leads, 21.4 against 14.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3.6 27B has a AA Agentic Index result, 18.5.
Directional only
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
Qwen3.6 27B
Qwen3.6 27B takes 262K tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 4.7 Flash
GLM 4.7 Flash $0.0003, Qwen3.6 27B $0.0018 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.6 27B has the number, $1.30.
Directional only
At a glance
- Coding index
- GLM 4.7 Flash not benchmarked, Qwen3.6 27B 36.8 from 2 benchmarks.
- Widest category
- Math, 32.8 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): GLM 4.7 Flash 41.7% against Qwen3.6 27B 77.3%, 35.7 points apart on a 0 to 100 scale.
- Output price
- GLM 4.7 Flash $0.40 against Qwen3.6 27B $2.70 per million output tokens, 6.8x apart.
- Context window
- GLM 4.7 Flash takes 200K tokens, Qwen3.6 27B 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 4.7 Flash | Bars | Qwen3.6 27B | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 1 | ||
| General | 0 | 2 | ||
| All shared boards | 1 | 8 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | GLM 4.7 Flash | Qwen3.6 27B | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 53.7 | Only Qwen3.6 27B measured |
| SWE-bench Verified (Vals AI) | Not measured | 70.0% | Only Qwen3.6 27B measured |
| Vibe Code Bench (Vals AI) | Not measured | 11.9% | Only Qwen3.6 27B measured |
| SciCode | Not measured | 42.8% | Only Qwen3.6 27B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 22.0% | 34.8% | Qwen3.6 27B |
| LMArena Text: coding | 1382 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: software and IT | 1389 | Not measured | Only GLM 4.7 Flash measured |
| Neither model has a result on the other 32 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 4.7 Flash | Qwen3.6 27B | Leader |
|---|---|---|---|
| AA Intelligence Index | 14.9 | 21.4 | Qwen3.6 27B |
| Epoch Capabilities Index | Not measured | 146.2 | Only Qwen3.6 27B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 4.7 Flash | Qwen3.6 27B | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 18.5 | Only Qwen3.6 27B measured |
| τ²-Bench Telecom | 98.8% | 94.2% | GLM 4.7 Flash |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GLM 4.7 Flash | Qwen3.6 27B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 58.1% | 84.2% | Qwen3.6 27B |
| Humanity's Last Exam (Artificial Analysis run) | 7.6% | 23.1% | Qwen3.6 27B |
| GPQA Diamond (Epoch AI run) | 60.5% | 85.9% | Qwen3.6 27B |
| Mystery game puzzles | Not measured | 7.0% | Only Qwen3.6 27B measured |
| LMArena Text: hard prompts | 1356 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: expert | 1357 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: hard prompts in English | 1369 | Not measured | Only GLM 4.7 Flash measured |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 4.7 Flash | Qwen3.6 27B | Leader |
|---|---|---|---|
| OTIS Mock AIME | 58.3% | 91.1% | Qwen3.6 27B |
| FrontierMath, tiers 1 to 3 | Not measured | 35.1% | Only Qwen3.6 27B measured |
| LMArena Text: math | 1355 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: mathematical work | 1369 | Not measured | Only GLM 4.7 Flash measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GLM 4.7 Flash | Qwen3.6 27B | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | Not measured | 53.2% | Only Qwen3.6 27B measured |
| CorpFin (Vals AI) | Not measured | 62.3% | Only Qwen3.6 27B measured |
| TaxEval (Vals AI) | Not measured | 71.3% | Only Qwen3.6 27B measured |
| MortgageTax (Vals AI) | Not measured | 68.3% | Only Qwen3.6 27B measured |
| LMArena Text: science | 1358 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: medicine and healthcare | 1343 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: legal and government | 1357 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: business and finance | 1343 | Not measured | Only GLM 4.7 Flash measured |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | GLM 4.7 Flash | Qwen3.6 27B | Leader |
|---|---|---|---|
| Design Arena: websites | 1194 | Not measured | Only GLM 4.7 Flash measured |
| Design Arena: UI components | 1205 | Not measured | Only GLM 4.7 Flash measured |
| Design Arena: game dev | 1134 | Not measured | Only GLM 4.7 Flash measured |
| Design Arena: data viz | 1123 | Not measured | Only GLM 4.7 Flash measured |
| Design Arena: 3D | 1120 | Not measured | Only GLM 4.7 Flash measured |
| Design Arena: all code categories | 1177 | Not measured | Only GLM 4.7 Flash measured |
| Design Arena: SVG | 1037 | Not measured | 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 index02
| Benchmark | GLM 4.7 Flash | Qwen3.6 27B | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 45.6% | Only Qwen3.6 27B measured |
| IFBench | 60.8% | 67.6% | Qwen3.6 27B |
| Long context reasoning (AA-LCR) | 41.7% | 77.3% | Qwen3.6 27B |
| DTBench | Not measured | 78.1% | Only Qwen3.6 27B measured |
| LMCA | Not measured | 34.5% | Only Qwen3.6 27B measured |
| LMArena Text | 1351 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: instruction following | 1327 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: creative writing | 1296 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: English | 1373 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: non-English | 1330 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: Chinese | 1403 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: German | 1336 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: Korean | 1283 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: French | 1332 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: Spanish | 1350 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: Russian | 1333 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: Polish | 1291 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: multi-turn | 1342 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: longer queries | 1345 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: writing and language | 1320 | Not measured | Only GLM 4.7 Flash measured |
| LMArena Text: entertainment and media | 1304 | Not measured | Only GLM 4.7 Flash measured |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 4.7 Flash | Qwen3.6 27B | 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 4.7 Flash | Qwen3.6 27B |
|---|---|---|
| Maker | Z.ai | Qwen |
| Weights | Open weights | Open weights |
| Released | January 19, 2026 | April 27, 2026 |
| Context window | 200K | 262K |
| Input $/Mtok | $0.0653 | $0.45 |
| Output $/Mtok | $0.40 | $2.70 |
| Coding index | Not benchmarked | 36.8 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | Not computable | $1.30 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.7 Flash better than Qwen3.6 27B for coding?
Only Qwen3.6 27B has a coding score, 36.8 on the Vibe Coding Index; GLM 4.7 Flash has none, so the two cannot be ranked on coding. Pick GLM 4.7 Flash for output tokens 6.8x cheaper ($0.40 vs $2.70 per million) and work measured by τ²-Bench Telecom, where it leads.
Which is cheaper, GLM 4.7 Flash or Qwen3.6 27B?
GLM 4.7 Flash costs $0.0653 per million input tokens and $0.40 per million output tokens; Qwen3.6 27B costs $0.45 and $2.70. Cost per solved task is known for Qwen3.6 27B only.
Which has the bigger context window, GLM 4.7 Flash or Qwen3.6 27B?
Qwen3.6 27B, with 262K tokens against 200K.
How many benchmarks is the GLM 4.7 Flash vs Qwen3.6 27B comparison based on?
9 benchmarks have a result for both models as of October 22, 2026. GLM 4.7 Flash's coding index rests on 0 independent benchmarks and Qwen3.6 27B's on 2. Where only one model has a result, the page says so instead of naming a winner.