Qwen3.5-27B vs Qwen3.8 27B
Updated October 21, 2026. 45 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 22.6 for Qwen3.5-27B.
Qwen3.5-27B is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 45
- Qwen3.5-27B only
- 8
- Qwen3.8 27B only
- 40
- 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, four public coding benchmarks
Qwen3.8 27B
Qwen3.8 27B scores 73.6 against 22.6.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Qwen3.8 27B
Qwen3.8 27B leads, 33.7 against 22.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3.8 27B has a AA Agentic Index result, 45.8.
Directional only
Reasoning
GPQA Diamond
No call
Only Qwen3.8 27B has a GPQA Diamond result, 88.9%.
Directional only
Knowledge
MMLU Pro
No call
Only Qwen3.8 27B has a MMLU Pro result, 84.3%.
Directional only
Long documents
Listed context window
Qwen3.8 27B
Qwen3.8 27B takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.8 27B
Qwen3.5-27B $0.0014, Qwen3.8 27B $0.0007 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.8 27B has the number, $1.26.
Directional only
At a glance
- Coding index
- Qwen3.5-27B 22.6 from 1 benchmark, Qwen3.8 27B 73.6 from 2 benchmarks.
- Widest category
- Coding, 24.8 points apart on average over 5 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: Qwen3.5-27B 1346 against Qwen3.8 27B 1602, 42.3 points apart on a 0 to 100 scale.
- Output price
- Qwen3.5-27B $2.16 against Qwen3.8 27B $1.35 per million output tokens, 1.6x apart.
- Context window
- Qwen3.5-27B takes 262K tokens, Qwen3.8 27B 1M.
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 | Qwen3.5-27B | Bars | Qwen3.8 27B | Ties |
|---|---|---|---|---|
| Coding | 0 | 5 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 7 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 26 | ||
| All shared boards | 0 | 45 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index05
| Benchmark | Qwen3.5-27B | Qwen3.8 27B | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 86.8% | Only Qwen3.8 27B measured |
| LMArena WebDev | 1358 | 1593 | Qwen3.8 27B |
| AA Coding Index | Not measured | 68.1 | Only Qwen3.8 27B measured |
| LiveCodeBench (Vals AI) | Not measured | 84.0% | Only Qwen3.8 27B measured |
| SWE-bench Verified (Vals AI) | Not measured | 86.0% | Only Qwen3.8 27B measured |
| Vibe Code Bench (Vals AI) | Not measured | 64.8% | Only Qwen3.8 27B measured |
| Code migration (Vals AI) | Not measured | 14.2% | Only Qwen3.8 27B measured |
| 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) | Not measured | 58.4% | Only Qwen3.8 27B measured |
| 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 | Not measured | 46.6% | Only Qwen3.8 27B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 32.6% | Not measured | Only Qwen3.5-27B measured |
| WeirdML | 39.5% | Not measured | Only Qwen3.5-27B measured |
| ALE-Bench | 349.4 | Not measured | Only Qwen3.5-27B measured |
| LMArena Text: coding | 1427 | 1483 | Qwen3.8 27B |
| LMArena Text: software and IT | 1431 | 1478 | Qwen3.8 27B |
| LMArena WebDev: React | 1346 | 1602 | Qwen3.8 27B |
| LMArena WebDev: HTML | 1386 | 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 17 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.5-27B | Qwen3.8 27B | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.9 | 33.7 | Qwen3.8 27B |
| Epoch Capabilities Index | Not measured | 151.7 | Only Qwen3.8 27B measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
| Benchmark | Qwen3.5-27B | Qwen3.8 27B | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 45.8 | Only Qwen3.8 27B 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) | Not measured | 48.5% | Only Qwen3.8 27B measured |
| Tax Agent Bench (Vals AI) | Not measured | 30.9% | Only Qwen3.8 27B measured |
| Legal Research Bench (Vals AI) | Not measured | 36.1% | Only Qwen3.8 27B measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 59.7% | Only Qwen3.8 27B measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 0.0% | Only Qwen3.8 27B measured |
| τ²-Bench Telecom | 93.9% | Not measured | Only Qwen3.5-27B measured |
| APEX-Agents | Not measured | 47.5% | Only Qwen3.8 27B measured |
| Vending-Bench 2 | $202 | Not measured | Only Qwen3.5-27B measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | Qwen3.5-27B | Qwen3.8 27B | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 88.9% | Only Qwen3.8 27B measured |
| 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) | 85.8% | 90.5% | Qwen3.8 27B |
| Humanity's Last Exam (Artificial Analysis run) | 23.9% | 33.9% | Qwen3.8 27B |
| ARC-AGI | Not measured | 87.5% | Only Qwen3.8 27B measured |
| ARC-AGI-2 | Not measured | 42.4% | Only Qwen3.8 27B measured |
| LMArena Text: hard prompts | 1415 | 1459 | Qwen3.8 27B |
| LMArena Text: expert | 1427 | 1479 | Qwen3.8 27B |
| LMArena Text: hard prompts in English | 1429 | 1461 | Qwen3.8 27B |
| LMArena Vision: diagrams | 1249 | 1285 | Qwen3.8 27B |
| LMArena Vision: homework | 1256 | 1295 | Qwen3.8 27B |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen3.5-27B | Qwen3.8 27B | Leader |
|---|---|---|---|
| ProofBench | Not measured | 16.0% | Only Qwen3.8 27B measured |
| LMArena Text: math | 1429 | 1455 | Qwen3.8 27B |
| LMArena Text: mathematical work | 1429 | 1458 | Qwen3.8 27B |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Qwen3.5-27B | Qwen3.8 27B | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 84.3% | Only Qwen3.8 27B measured |
| LegalBench (Vals AI) | Not measured | 82.4% | Only Qwen3.8 27B measured |
| TaxEval (Vals AI) | Not measured | 70.8% | Only Qwen3.8 27B measured |
| MortgageTax (Vals AI) | Not measured | 64.9% | Only Qwen3.8 27B measured |
| MedCode (Vals AI) | Not measured | 28.7% | Only Qwen3.8 27B measured |
| LMArena Text: science | 1437 | 1467 | Qwen3.8 27B |
| LMArena Text: medicine and healthcare | 1425 | 1437 | Qwen3.8 27B |
| LMArena Text: legal and government | 1405 | 1447 | Qwen3.8 27B |
| LMArena Text: business and finance | 1399 | 1438 | Qwen3.8 27B |
| Neither model has a result on the other 8 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Qwen3.5-27B | Qwen3.8 27B | Leader |
|---|---|---|---|
| LiveBench design | Not measured | 75.9% | Only Qwen3.8 27B measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index026
| Benchmark | Qwen3.5-27B | 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) | Not measured | 83.8% | Only Qwen3.8 27B measured |
| IFBench | 75.6% | Not measured | Only Qwen3.5-27B measured |
| Long context reasoning (AA-LCR) | 77.7% | 82.0% | Qwen3.8 27B |
| DTBench | 82.4% | 88.0% | Qwen3.8 27B |
| LMCA | 34.0% | 41.4% | Qwen3.8 27B |
| Surface Evolver Bench | Not measured | 45.0% | Only Qwen3.8 27B measured |
| LMArena Text | 1409 | 1440 | Qwen3.8 27B |
| LMArena Text: instruction following | 1393 | 1436 | Qwen3.8 27B |
| LMArena Text: creative writing | 1362 | 1383 | Qwen3.8 27B |
| LMArena Vision | 1241 | 1269 | Qwen3.8 27B |
| LMArena Text: English | 1425 | 1448 | Qwen3.8 27B |
| LMArena Text: non-English | 1390 | 1428 | Qwen3.8 27B |
| LMArena Text: Chinese | 1478 | 1501 | Qwen3.8 27B |
| LMArena Text: German | 1392 | 1443 | Qwen3.8 27B |
| LMArena Text: Japanese | 1346 | 1387 | Qwen3.8 27B |
| LMArena Text: Korean | 1359 | 1384 | Qwen3.8 27B |
| LMArena Text: French | 1410 | 1465 | Qwen3.8 27B |
| LMArena Text: Spanish | 1407 | 1449 | Qwen3.8 27B |
| LMArena Text: Russian | 1390 | 1415 | Qwen3.8 27B |
| LMArena Text: Polish | 1375 | 1439 | Qwen3.8 27B |
| LMArena Text: multi-turn | 1410 | 1440 | Qwen3.8 27B |
| LMArena Text: longer queries | 1413 | 1448 | Qwen3.8 27B |
| LMArena Text: writing and language | 1380 | 1405 | Qwen3.8 27B |
| LMArena Text: entertainment and media | 1363 | 1393 | Qwen3.8 27B |
| LMArena Vision: English | 1246 | 1267 | Qwen3.8 27B |
| LMArena Vision: Chinese | 1301 | 1326 | Qwen3.8 27B |
| LMArena Vision: reading text | 1246 | 1281 | Qwen3.8 27B |
| LMArena Vision: humor | 1227 | 1235 | Qwen3.8 27B |
| LMArena Vision: captioning | 1170 | Not measured | Only Qwen3.5-27B measured |
| LMArena Vision: recognizing things | 1210 | Not measured | Only Qwen3.5-27B measured |
| LMArena Vision: creative writing | 1224 | 1237 | Qwen3.8 27B |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.5-27B | 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 | Qwen3.5-27B | Qwen3.8 27B |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | Open weights | Open weights |
| Released | February 25, 2026 | August 14, 2026 |
| Context window | 262K | 1M |
| Input $/Mtok | $0.27 | $0.04 |
| Output $/Mtok | $2.16 | $1.35 |
| Coding index | 22.6 | 73.6 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | $1.26 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.5-27B better than Qwen3.8 27B for coding?
Pick Qwen3.8 27B for coding: it scores 73.6 on the Vibe Coding Index against 22.6 for Qwen3.5-27B. Qwen3.5-27B is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, Qwen3.5-27B or Qwen3.8 27B?
Qwen3.5-27B costs $0.27 per million input tokens and $2.16 per million output tokens; Qwen3.8 27B costs $0.04 and $1.35. Cost per solved task is known for Qwen3.8 27B only.
Which has the bigger context window, Qwen3.5-27B or Qwen3.8 27B?
Qwen3.8 27B, with 1M tokens against 262K.
How many benchmarks is the Qwen3.5-27B vs Qwen3.8 27B comparison based on?
45 benchmarks have a result for both models as of October 21, 2026. Qwen3.5-27B'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.