Qwen3.5 Plus 2026-04-20 vs Qwen3.6 27B
Qwen3.5 Plus 2026-04-20 leads Qwen3.6 27B on coding, 39.5 to 36.8 on the Vibe Coding Index, and Qwen3.5 Plus 2026-04-20 costs 1.5x less per output token ($1.80 vs $2.70 per million). Updated October 22, 2026; 12 benchmarks have a result for both.
Qwen3.5 Plus 2026-04-20 or Qwen3.6 27B: which to pick
Pick Qwen3.5 Plus 2026-04-20 for coding: it scores 39.5 on the Vibe Coding Index against 36.8 for Qwen3.6 27B.
Pick Qwen3.6 27B for a lower cost per solved task ($1.30 against $1.35) and work measured by Epoch Capabilities Index or GPQA Diamond (Epoch AI run), where it leads.
- Shared results
- 12
- Qwen3.5 Plus 2026-04-20 only
- 13
- Qwen3.6 27B only
- 13
- 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
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 scores 39.5 against 36.8.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
No call
Only Qwen3.6 27B has a AA Intelligence Index result, 21.4.
Directional only
Agentic work
AA Agentic Index
No call
Only Qwen3.6 27B has a AA Agentic Index result, 18.5.
Directional only
Reasoning
GPQA Diamond
No call
Only Qwen3.5 Plus 2026-04-20 has a GPQA Diamond result, 87.4%.
Directional only
Math
AIME
No call
Only Qwen3.5 Plus 2026-04-20 has a AIME result, 86.0%.
Directional only
Knowledge
MMLU Pro
No call
Only Qwen3.5 Plus 2026-04-20 has a MMLU Pro result, 87.2%.
Directional only
Long documents
Listed context window
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5 Plus 2026-04-20
Qwen3.5 Plus 2026-04-20 $0.0012, Qwen3.6 27B $0.0018 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Qwen3.6 27B
Qwen3.5 Plus 2026-04-20 $1.35, Qwen3.6 27B $1.30.
Published attempt cost and pass rate
At a glance
- Coding index
- Qwen3.5 Plus 2026-04-20 39.5 from 2 benchmarks, Qwen3.6 27B 36.8 from 2 benchmarks.
- Widest category
- General, 6.5 points apart on average over 3 shared benchmarks.
- Widest single gap
- SAGE (Vals AI): Qwen3.5 Plus 2026-04-20 30.4% against Qwen3.6 27B 45.6%, 15.2 points apart on a 0 to 100 scale.
- Output price
- Qwen3.5 Plus 2026-04-20 $1.80 against Qwen3.6 27B $2.70 per million output tokens, 1.5x apart.
- Context window
- Qwen3.5 Plus 2026-04-20 takes 1M 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 | Qwen3.5 Plus 2026-04-20 | Bars | Qwen3.6 27B | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 1 | 1 | ||
| Math | 0 | 1 | ||
| Knowledge | 2 | 1 | ||
| General | 2 | 1 | ||
| All shared boards | 7 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Qwen3.5 Plus 2026-04-20 | Qwen3.6 27B | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 53.7 | Only Qwen3.6 27B measured |
| LiveCodeBench (Vals AI) | 85.3% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| SWE-bench Verified (Vals AI) | 71.2% | 70.0% | Qwen3.5 Plus 2026-04-20 |
| Vibe Code Bench (Vals AI) | 15.7% | 11.9% | Qwen3.5 Plus 2026-04-20 |
| SciCode | Not measured | 42.8% | Only Qwen3.6 27B measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 34.8% | Only Qwen3.6 27B measured |
| ALE-Bench | 608.9 | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| Neither model has a result on the other 36 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.5 Plus 2026-04-20 | Qwen3.6 27B | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 21.4 | Only Qwen3.6 27B measured |
| Epoch Capabilities Index | 146.2 | 146.2 | Qwen3.6 27B |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Qwen3.5 Plus 2026-04-20 | Qwen3.6 27B | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 18.5 | Only Qwen3.6 27B measured |
| τ²-Bench Telecom | Not measured | 94.2% | Only Qwen3.6 27B measured |
| Vending-Bench 2 | $1 | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Qwen3.5 Plus 2026-04-20 | Qwen3.6 27B | Leader |
|---|---|---|---|
| GPQA Diamond | 87.4% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| MMMU Pro (Vals AI) | 22.8% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 84.2% | Only Qwen3.6 27B measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 23.1% | Only Qwen3.6 27B measured |
| GPQA Diamond (Epoch AI run) | 84.8% | 85.9% | Qwen3.6 27B |
| Chess puzzles | 8.0% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| Mystery game puzzles | 17.0% | 7.0% | Qwen3.5 Plus 2026-04-20 |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.5 Plus 2026-04-20 | Qwen3.6 27B | Leader |
|---|---|---|---|
| AIME | 86.0% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| OTIS Mock AIME | 86.7% | 91.1% | Qwen3.6 27B |
| FrontierMath, tiers 1 to 3 | Not measured | 35.1% | Only Qwen3.6 27B measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Qwen3.5 Plus 2026-04-20 | Qwen3.6 27B | Leader |
|---|---|---|---|
| MMLU Pro | 87.2% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| LegalBench (Vals AI) | 85.1% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| CaseLaw (Vals AI) | 59.7% | 53.2% | Qwen3.5 Plus 2026-04-20 |
| CorpFin (Vals AI) | 65.3% | 62.3% | Qwen3.5 Plus 2026-04-20 |
| TaxEval (Vals AI) | Not measured | 71.3% | Only Qwen3.6 27B measured |
| MortgageTax (Vals AI) | 60.8% | 68.3% | Qwen3.6 27B |
| MedQA (Vals AI) | 95.2% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| SimpleQA Verified | 25.4% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| Neither model has a result on the other 12 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.5 Plus 2026-04-20 | Qwen3.6 27B | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Qwen3.5 Plus 2026-04-20 | Qwen3.6 27B | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 30.4% | 45.6% | Qwen3.6 27B |
| IFBench | Not measured | 67.6% | Only Qwen3.6 27B measured |
| Long context reasoning (AA-LCR) | Not measured | 77.3% | Only Qwen3.6 27B measured |
| DTBench | 80.5% | 78.1% | Qwen3.5 Plus 2026-04-20 |
| LMCA | 36.4% | 34.5% | Qwen3.5 Plus 2026-04-20 |
| CL-bench | 19.8% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| CL-bench Life | 12.4% | Not measured | Only Qwen3.5 Plus 2026-04-20 measured |
| EQ-Bench 4 | Not measured | 1026 | Only Qwen3.6 27B measured |
| Neither model has a result on the other 40 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.5 Plus 2026-04-20 | 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
Qwen3.5 Plus 2026-04-20 costs less
Repository review
50K input + 3K output tokens
Qwen3.5 Plus 2026-04-20 costs less
Agent loop
200K input + 10K output tokens
Qwen3.5 Plus 2026-04-20 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 Plus 2026-04-20 | Qwen3.6 27B |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | No public weights listed | Open weights |
| Released | April 27, 2026 | April 27, 2026 |
| Context window | 1M | 262K |
| Input $/Mtok | $0.30 | $0.45 |
| Output $/Mtok | $1.80 | $2.70 |
| Coding index | 39.5 | 36.8 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $1.35 | $1.30 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.5 Plus 2026-04-20 better than Qwen3.6 27B for coding?
Pick Qwen3.5 Plus 2026-04-20 for coding: it scores 39.5 on the Vibe Coding Index against 36.8 for Qwen3.6 27B. Pick Qwen3.6 27B for a lower cost per solved task ($1.30 against $1.35) and work measured by Epoch Capabilities Index or GPQA Diamond (Epoch AI run), where it leads.
Which is cheaper, Qwen3.5 Plus 2026-04-20 or Qwen3.6 27B?
Qwen3.5 Plus 2026-04-20 costs $0.30 per million input tokens and $1.80 per million output tokens; Qwen3.6 27B costs $0.45 and $2.70. Per solved SWE-bench Verified task, Qwen3.5 Plus 2026-04-20 costs $1.35 and Qwen3.6 27B $1.30.
Which has the bigger context window, Qwen3.5 Plus 2026-04-20 or Qwen3.6 27B?
Qwen3.5 Plus 2026-04-20, with 1M tokens against 262K.
How many benchmarks is the Qwen3.5 Plus 2026-04-20 vs Qwen3.6 27B comparison based on?
12 benchmarks have a result for both models as of October 22, 2026. Qwen3.5 Plus 2026-04-20's coding index rests on 2 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.