Qwen3.7 Max vs Qwen3.8 27B
Updated October 21, 2026. 29 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Qwen3.8 27B for coding: it scores 73.6 on the Vibe Coding Index against 45.1 for Qwen3.7 Max.
Pick Qwen3.7 Max when what matters is LiveCodeBench (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.
- Shared results
- 29
- Qwen3.7 Max only
- 30
- Qwen3.8 27B only
- 56
- Like-for-like categories
- 7 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, four public coding benchmarks
Qwen3.8 27B
Qwen3.8 27B scores 73.6 against 45.1.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Qwen3.8 27B
Qwen3.8 27B leads, 33.7 against 29.5.
Same board, both measured
Agentic work
AA Agentic Index
Qwen3.8 27B
Qwen3.8 27B leads, 45.8 against 22.5.
Same board, both measured
Reasoning
GPQA Diamond
Qwen3.7 Max
Qwen3.7 Max leads, 90.2% against 88.9%.
Same board, both measured
Knowledge
MMLU Pro
Qwen3.7 Max
Qwen3.7 Max leads, 89.3% against 84.3%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Qwen3.7 Max has a Design Arena: websites result, 1274.
Directional only
Long documents
Listed context window
No call
Both take 1M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.8 27B
Qwen3.7 Max $0.0037, Qwen3.8 27B $0.0007 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Qwen3.8 27B
Qwen3.7 Max $4.69, Qwen3.8 27B $1.26.
Published attempt cost and pass rate
At a glance
- Coding index
- Qwen3.7 Max 45.1 from 1 benchmark, Qwen3.8 27B 73.6 from 2 benchmarks.
- Widest category
- Agentic work, 10.5 points apart on average over 5 shared benchmarks.
- Widest single gap
- AA Agentic Index: Qwen3.7 Max 22.5 against Qwen3.8 27B 45.8, 23.3 points apart on a 0 to 100 scale.
- Output price
- Qwen3.7 Max $4.425 against Qwen3.8 27B $1.35 per million output tokens, 3.3x apart.
- Context window
- Both take 1M tokens.
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 | Qwen3.7 Max | Bars | Qwen3.8 27B | Ties |
|---|---|---|---|---|
| Coding | 3 | 7 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 0 | 5 | ||
| Reasoning | 3 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 4 | 0 | ||
| General | 2 | 2 | ||
| All shared boards | 14 | 15 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index37
| Benchmark | Qwen3.7 Max | Qwen3.8 27B | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 86.8% | Only Qwen3.8 27B measured |
| LMArena WebDev | 1515 | 1593 | Qwen3.8 27B |
| AA Coding Index | 66.0 | 68.1 | Qwen3.8 27B |
| LiveCodeBench (Vals AI) | 87.1% | 84.0% | Qwen3.7 Max |
| SWE-bench Verified (Vals AI) | 68.8% | 86.0% | Qwen3.8 27B |
| Vibe Code Bench (Vals AI) | 47.7% | 64.8% | Qwen3.8 27B |
| Code migration (Vals AI) | 13.1% | 14.2% | Qwen3.8 27B |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Qwen3.8 27B measured |
| IOI (Vals AI) | Not measured | 39.1% | Only Qwen3.8 27B measured |
| Terminal-Bench 2.1 (Vals AI) | 61.0% | 58.4% | Qwen3.7 Max |
| SkillsBench (Vals AI) | Not measured | 38.1% | Only Qwen3.8 27B measured |
| CyberBench (Vals AI) | Not measured | 67.8% | Only Qwen3.8 27B measured |
| SciCode | 49.5% | 46.6% | Qwen3.7 Max |
| Terminal-Bench Hard (Artificial Analysis run) | 50.8% | Not measured | Only Qwen3.7 Max measured |
| ALE-Bench | 1189.4 | Not measured | Only Qwen3.7 Max measured |
| LMArena Text: coding | Not measured | 1483 | Only Qwen3.8 27B measured |
| LMArena Text: software and IT | Not measured | 1478 | Only Qwen3.8 27B measured |
| LMArena WebDev: React | 1514 | 1602 | Qwen3.8 27B |
| LMArena WebDev: HTML | 1512 | 1570 | Qwen3.8 27B |
| LMArena WebDev: from an image | Not measured | 1577 | Only Qwen3.8 27B measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Qwen3.7 Max | Qwen3.8 27B | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.5 | 33.7 | Qwen3.8 27B |
| Epoch Capabilities Index | 154.0 | 151.7 | Qwen3.7 Max |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Qwen3.7 Max | Qwen3.8 27B | Leader |
|---|---|---|---|
| AA Agentic Index | 22.5 | 45.8 | Qwen3.8 27B |
| Design Arena: agents building web apps | 1208 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building full-stack apps | 1191 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building mobile apps | 1153 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building Android apps | 1165 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building Godot games | 1187 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building games | 1161 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: HTML slides | 1158 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: PowerPoint slides | 1196 | Not measured | Only Qwen3.7 Max measured |
| LiveBench research | Not measured | 59.4% | Only Qwen3.8 27B measured |
| LiveBench browser | Not measured | 32.0% | Only Qwen3.8 27B measured |
| LiveBench long agentic | Not measured | 27.9% | Only Qwen3.8 27B measured |
| Finance Agent (Vals AI) | 47.8% | 48.5% | Qwen3.8 27B |
| Tax Agent Bench (Vals AI) | 15.8% | 30.9% | Qwen3.8 27B |
| Legal Research Bench (Vals AI) | 25.5% | 36.1% | Qwen3.8 27B |
| Excel Modeling Benchmark (Vals AI) | 57.0% | 59.7% | Qwen3.8 27B |
| Terminal-Bench-Science (Vals AI) | Not measured | 0.0% | Only Qwen3.8 27B measured |
| τ²-Bench Telecom | 94.7% | Not measured | Only Qwen3.7 Max measured |
| APEX-Agents | Not measured | 47.5% | Only Qwen3.8 27B measured |
| Neither model has a result on the other 20 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Qwen3.7 Max | Qwen3.8 27B | Leader |
|---|---|---|---|
| GPQA Diamond | 90.2% | 88.9% | Qwen3.7 Max |
| LiveBench reasoning | Not measured | 80.0% | Only Qwen3.8 27B measured |
| MMMU Pro (Vals AI) | Not measured | 83.9% | Only Qwen3.8 27B measured |
| GPQA Diamond (Artificial Analysis run) | 92.3% | 90.5% | Qwen3.7 Max |
| Humanity's Last Exam (Artificial Analysis run) | 40.5% | 33.9% | Qwen3.7 Max |
| GPQA Diamond (Epoch AI run) | 90.9% | Not measured | Only Qwen3.7 Max measured |
| ARC-AGI | Not measured | 87.5% | Only Qwen3.8 27B measured |
| ARC-AGI-2 | Not measured | 42.4% | Only Qwen3.8 27B measured |
| SimpleBench | 70.4% | Not measured | Only Qwen3.7 Max measured |
| Chess puzzles | 26.0% | Not measured | Only Qwen3.7 Max measured |
| Mystery game puzzles | 32.0% | Not measured | Only Qwen3.7 Max measured |
| EBR-bench | 9.5% | Not measured | Only Qwen3.7 Max measured |
| LMArena Text: hard prompts | Not measured | 1459 | Only Qwen3.8 27B measured |
| LMArena Text: expert | Not measured | 1479 | Only Qwen3.8 27B measured |
| LMArena Text: hard prompts in English | Not measured | 1461 | Only Qwen3.8 27B measured |
| LMArena Vision: diagrams | Not measured | 1285 | Only Qwen3.8 27B measured |
| LMArena Vision: homework | Not measured | 1295 | Only Qwen3.8 27B measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.7 Max | Qwen3.8 27B | Leader |
|---|---|---|---|
| OTIS Mock AIME | 95.6% | Not measured | Only Qwen3.7 Max measured |
| FrontierMath, tiers 1 to 3 | 64.6% | Not measured | Only Qwen3.7 Max measured |
| FrontierMath, tier 4 | 34.1% | Not measured | Only Qwen3.7 Max measured |
| ProofBench | 26.0% | 16.0% | Qwen3.7 Max |
| LMArena Text: math | Not measured | 1455 | Only Qwen3.8 27B measured |
| LMArena Text: mathematical work | Not measured | 1458 | Only Qwen3.8 27B measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Qwen3.7 Max | Qwen3.8 27B | Leader |
|---|---|---|---|
| MMLU Pro | 89.3% | 84.3% | Qwen3.7 Max |
| LegalBench (Vals AI) | 84.9% | 82.4% | Qwen3.7 Max |
| CorpFin (Vals AI) | 63.7% | Not measured | Only Qwen3.7 Max measured |
| TaxEval (Vals AI) | 75.3% | 70.8% | Qwen3.7 Max |
| MortgageTax (Vals AI) | Not measured | 64.9% | Only Qwen3.8 27B measured |
| MedCode (Vals AI) | 38.8% | 28.7% | Qwen3.7 Max |
| SimpleQA Verified | 55.8% | Not measured | Only Qwen3.7 Max measured |
| LMArena Text: science | Not measured | 1467 | Only Qwen3.8 27B measured |
| LMArena Text: medicine and healthcare | Not measured | 1437 | Only Qwen3.8 27B measured |
| LMArena Text: legal and government | Not measured | 1447 | Only Qwen3.8 27B measured |
| LMArena Text: business and finance | Not measured | 1438 | Only Qwen3.8 27B measured |
| Neither model has a result on the other 6 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Qwen3.7 Max | Qwen3.8 27B | Leader |
|---|---|---|---|
| Design Arena: websites | 1274 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: UI components | 1269 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: game dev | 1265 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: data viz | 1275 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: 3D | 1266 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: all code categories | 1275 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: SVG | 1216 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: ASCII art | 1211 | Not measured | Only Qwen3.7 Max measured |
| LiveBench design | Not measured | 75.9% | Only Qwen3.8 27B measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | Qwen3.7 Max | Qwen3.8 27B | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 76.6% | Only Qwen3.8 27B measured |
| SAGE (Vals AI) | Not measured | 52.4% | Only Qwen3.8 27B measured |
| MedScribe (Vals AI) | 79.4% | 83.8% | Qwen3.8 27B |
| IFBench | 80.5% | Not measured | Only Qwen3.7 Max measured |
| Long context reasoning (AA-LCR) | 79.0% | 82.0% | Qwen3.8 27B |
| DTBench | 92.3% | 88.0% | Qwen3.7 Max |
| LMCA | 44.0% | 41.4% | Qwen3.7 Max |
| Surface Evolver Bench | Not measured | 45.0% | Only Qwen3.8 27B measured |
| LMArena Text | Not measured | 1440 | Only Qwen3.8 27B measured |
| LMArena Text: instruction following | Not measured | 1436 | Only Qwen3.8 27B measured |
| LMArena Text: creative writing | Not measured | 1383 | Only Qwen3.8 27B measured |
| LMArena Vision | Not measured | 1269 | Only Qwen3.8 27B measured |
| LMArena Text: English | Not measured | 1448 | Only Qwen3.8 27B measured |
| LMArena Text: non-English | Not measured | 1428 | Only Qwen3.8 27B measured |
| LMArena Text: Chinese | Not measured | 1501 | Only Qwen3.8 27B measured |
| LMArena Text: German | Not measured | 1443 | Only Qwen3.8 27B measured |
| LMArena Text: Japanese | Not measured | 1387 | Only Qwen3.8 27B measured |
| LMArena Text: Korean | Not measured | 1384 | Only Qwen3.8 27B measured |
| LMArena Text: French | Not measured | 1465 | Only Qwen3.8 27B measured |
| LMArena Text: Spanish | Not measured | 1449 | Only Qwen3.8 27B measured |
| LMArena Text: Russian | Not measured | 1415 | Only Qwen3.8 27B measured |
| LMArena Text: Polish | Not measured | 1439 | Only Qwen3.8 27B measured |
| LMArena Text: multi-turn | Not measured | 1440 | Only Qwen3.8 27B measured |
| LMArena Text: longer queries | Not measured | 1448 | Only Qwen3.8 27B measured |
| LMArena Text: writing and language | Not measured | 1405 | Only Qwen3.8 27B measured |
| LMArena Text: entertainment and media | Not measured | 1393 | Only Qwen3.8 27B measured |
| LMArena Vision: English | Not measured | 1267 | Only Qwen3.8 27B measured |
| LMArena Vision: Chinese | Not measured | 1326 | Only Qwen3.8 27B measured |
| LMArena Vision: reading text | Not measured | 1281 | Only Qwen3.8 27B measured |
| LMArena Vision: humor | Not measured | 1235 | Only Qwen3.8 27B measured |
| LMArena Vision: creative writing | Not measured | 1237 | Only Qwen3.8 27B measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.7 Max | Qwen3.8 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
Qwen3.8 27B costs less
Repository review
50K input + 3K output tokens
Qwen3.8 27B costs less
Agent loop
200K input + 10K output tokens
Qwen3.8 27B 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 | Qwen3.7 Max | Qwen3.8 27B |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | No public weights listed | Open weights |
| Released | May 21, 2026 | August 14, 2026 |
| Context window | 1M | 1M |
| Input $/Mtok | $1.475 | $0.04 |
| Output $/Mtok | $4.425 | $1.35 |
| Coding index | 45.1 | 73.6 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $4.69 | $1.26 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.7 Max better than Qwen3.8 27B for coding?
Pick Qwen3.8 27B for coding: it scores 73.6 on the Vibe Coding Index against 45.1 for Qwen3.7 Max. Pick Qwen3.7 Max when what matters is LiveCodeBench (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.
Which is cheaper, Qwen3.7 Max or Qwen3.8 27B?
Qwen3.7 Max costs $1.475 per million input tokens and $4.425 per million output tokens; Qwen3.8 27B costs $0.04 and $1.35. Per solved SWE-bench Verified task, Qwen3.7 Max costs $4.69 and Qwen3.8 27B $1.26.
Which has the bigger context window, Qwen3.7 Max or Qwen3.8 27B?
Neither: both take 1M tokens.
How many benchmarks is the Qwen3.7 Max vs Qwen3.8 27B comparison based on?
29 benchmarks have a result for both models as of October 21, 2026. Qwen3.7 Max's coding index rests on 1 independent benchmark and Qwen3.8 27B's on 2. Where only one model has a result, the page says so instead of naming a winner.