DeepSeek V3.2 vs Qwen3.5-Flash
Updated October 21, 2026. 43 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick DeepSeek V3.2 for coding: it scores 54.4 on the Vibe Coding Index against 6.2 for Qwen3.5-Flash.
Pick Qwen3.5-Flash when output tokens cost 1.6x less, or when a solved task costs $0.40 against $0.99.
- Shared results
- 43
- DeepSeek V3.2 only
- 32
- Qwen3.5-Flash only
- 12
- 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
DeepSeek V3.2
DeepSeek V3.2 scores 54.4 against 6.2.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only DeepSeek V3.2 has a AA Intelligence Index result, 21.5.
Directional only
Reasoning
GPQA Diamond
Qwen3.5-Flash
Qwen3.5-Flash leads, 82.8% against 80.3%.
Same board, both measured
Math
AIME
Qwen3.5-Flash
Qwen3.5-Flash leads, 92.5% against 84.6%.
Same board, both measured
Knowledge
MMLU Pro
DeepSeek V3.2
DeepSeek V3.2 leads, 84.9% against 84.1%.
Same board, both measured
Web design
Design Arena: websites
No call
Only DeepSeek V3.2 has a Design Arena: websites result, 1175.
Directional only
Long documents
Listed context window
Qwen3.5-Flash
Qwen3.5-Flash takes 1M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5-Flash
DeepSeek V3.2 $0.0005, Qwen3.5-Flash $0.0002 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Qwen3.5-Flash
DeepSeek V3.2 $0.99, Qwen3.5-Flash $0.40.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V3.2 54.4 from 2 benchmarks, Qwen3.5-Flash 6.2 from 1 benchmark.
- Widest category
- Coding, 9.8 points apart on average over 7 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: DeepSeek V3.2 1350 against Qwen3.5-Flash 1229, 20.1 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.42 against Qwen3.5-Flash $0.26 per million output tokens, 1.6x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, Qwen3.5-Flash 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 | DeepSeek V3.2 | Bars | Qwen3.5-Flash | Ties |
|---|---|---|---|---|
| Coding | 6 | 1 | ||
| Intelligence | 1 | 0 | ||
| Reasoning | 3 | 1 | ||
| Math | 2 | 1 | ||
| Knowledge | 5 | 4 | ||
| General | 18 | 1 | ||
| All shared boards | 35 | 8 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index61
| Benchmark | DeepSeek V3.2 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.0% | Not measured | Only DeepSeek V3.2 measured |
| SWE-bench Multilingual | 59.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev | 1362 | 1244 | DeepSeek V3.2 |
| AA Coding Index | 44.2 | Not measured | Only DeepSeek V3.2 measured |
| LiveCodeBench (Vals AI) | 80.7% | 83.3% | Qwen3.5-Flash |
| SWE-bench Verified (Vals AI) | 67.6% | 64.4% | DeepSeek V3.2 |
| Vibe Code Bench (Vals AI) | 5.1% | Not measured | Only DeepSeek V3.2 measured |
| LiveCodeBench (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | Not measured | Only DeepSeek V3.2 measured |
| Terminal-Bench | 39.6% | Not measured | Only DeepSeek V3.2 measured |
| ALE-Bench | Not measured | 265.9 | Only Qwen3.5-Flash measured |
| LMArena Text: coding | 1453 | 1412 | DeepSeek V3.2 |
| LMArena Text: software and IT | 1449 | 1416 | DeepSeek V3.2 |
| LMArena WebDev: React | 1350 | 1229 | DeepSeek V3.2 |
| LMArena WebDev: HTML | 1371 | 1291 | DeepSeek V3.2 |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3.2 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | Not measured | Only DeepSeek V3.2 measured |
| Epoch Capabilities Index | 146.1 | 143.5 | DeepSeek V3.2 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | DeepSeek V3.2 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 90.6% | Not measured | Only DeepSeek V3.2 measured |
| APEX-Agents | 21.3% | Not measured | Only DeepSeek V3.2 measured |
| Vending-Bench 2 | $1,034 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | DeepSeek V3.2 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | 82.8% | Qwen3.5-Flash |
| MMMU Pro (Vals AI) | Not measured | 81.9% | Only Qwen3.5-Flash measured |
| GPQA Diamond (Artificial Analysis run) | 84.0% | Not measured | Only DeepSeek V3.2 measured |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | Not measured | Only DeepSeek V3.2 measured |
| GPQA Diamond (Epoch AI run) | Not measured | 82.3% | Only Qwen3.5-Flash measured |
| ARC-AGI | 57.0% | Not measured | Only DeepSeek V3.2 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only DeepSeek V3.2 measured |
| Chess puzzles | Not measured | 14.0% | Only Qwen3.5-Flash measured |
| Mystery game puzzles | Not measured | 20.0% | Only Qwen3.5-Flash measured |
| LMArena Text: hard prompts | 1434 | 1403 | DeepSeek V3.2 |
| LMArena Text: expert | 1436 | 1407 | DeepSeek V3.2 |
| LMArena Text: hard prompts in English | 1446 | 1409 | DeepSeek V3.2 |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | DeepSeek V3.2 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| AIME | 84.6% | 92.5% | Qwen3.5-Flash |
| MGSM (Vals AI) | 86.0% | Not measured | Only DeepSeek V3.2 measured |
| AA Math Index | 92.0 | Not measured | Only DeepSeek V3.2 measured |
| AIME 2025 (Artificial Analysis run) | 92.0% | Not measured | Only DeepSeek V3.2 measured |
| OTIS Mock AIME | Not measured | 84.4% | Only Qwen3.5-Flash measured |
| FrontierMath, tiers 1 to 3 | Not measured | 18.2% | Only Qwen3.5-Flash measured |
| LMArena Text: math | 1435 | 1407 | DeepSeek V3.2 |
| LMArena Text: mathematical work | 1440 | 1413 | DeepSeek V3.2 |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index54
| Benchmark | DeepSeek V3.2 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | 84.1% | DeepSeek V3.2 |
| LegalBench (Vals AI) | 76.1% | 84.3% | Qwen3.5-Flash |
| CaseLaw (Vals AI) | 55.4% | 56.0% | Qwen3.5-Flash |
| CorpFin (Vals AI) | 51.0% | 63.6% | Qwen3.5-Flash |
| TaxEval (Vals AI) | 68.2% | 72.2% | Qwen3.5-Flash |
| MortgageTax (Vals AI) | Not measured | 67.4% | Only Qwen3.5-Flash measured |
| MedQA (Vals AI) | 93.9% | Not measured | Only DeepSeek V3.2 measured |
| MedCode (Vals AI) | Not measured | 33.0% | Only Qwen3.5-Flash measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SimpleQA Verified | Not measured | 20.3% | Only Qwen3.5-Flash measured |
| LMArena Text: science | 1446 | 1415 | DeepSeek V3.2 |
| LMArena Text: medicine and healthcare | 1440 | 1407 | DeepSeek V3.2 |
| LMArena Text: legal and government | 1425 | 1398 | DeepSeek V3.2 |
| LMArena Text: business and finance | 1410 | 1394 | DeepSeek V3.2 |
| Neither model has a result on the other 3 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V3.2 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: UI components | 1149 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: game dev | 1132 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: data viz | 1158 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: 3D | 1133 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: all code categories | 1164 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: SVG | 1032 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: ASCII art | 1082 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index181
| Benchmark | DeepSeek V3.2 | Qwen3.5-Flash | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 42.5% | Only Qwen3.5-Flash measured |
| MedScribe (Vals AI) | Not measured | 70.6% | Only Qwen3.5-Flash measured |
| IFBench | 60.7% | Not measured | Only DeepSeek V3.2 measured |
| Long context reasoning (AA-LCR) | 73.3% | Not measured | Only DeepSeek V3.2 measured |
| DTBench | 85.6% | 82.9% | DeepSeek V3.2 |
| LMCA | 28.8% | 29.1% | Qwen3.5-Flash |
| CL-bench | 12.4% | Not measured | Only DeepSeek V3.2 measured |
| CL-bench Life | 7.4% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text | 1425 | 1397 | DeepSeek V3.2 |
| LMArena Text: instruction following | 1413 | 1374 | DeepSeek V3.2 |
| LMArena Text: creative writing | 1400 | 1343 | DeepSeek V3.2 |
| LMArena Text: English | 1439 | 1404 | DeepSeek V3.2 |
| LMArena Text: non-English | 1409 | 1385 | DeepSeek V3.2 |
| LMArena Text: Chinese | 1455 | 1445 | DeepSeek V3.2 |
| LMArena Text: German | 1413 | 1390 | DeepSeek V3.2 |
| LMArena Text: Japanese | 1374 | 1369 | DeepSeek V3.2 |
| LMArena Text: Korean | 1370 | 1344 | DeepSeek V3.2 |
| LMArena Text: French | 1429 | 1413 | DeepSeek V3.2 |
| LMArena Text: Spanish | 1424 | 1400 | DeepSeek V3.2 |
| LMArena Text: Russian | 1424 | 1380 | DeepSeek V3.2 |
| LMArena Text: Polish | 1419 | 1376 | DeepSeek V3.2 |
| LMArena Text: multi-turn | 1427 | 1393 | DeepSeek V3.2 |
| LMArena Text: longer queries | 1428 | 1392 | DeepSeek V3.2 |
| LMArena Text: writing and language | 1407 | 1369 | DeepSeek V3.2 |
| LMArena Text: entertainment and media | 1395 | 1347 | DeepSeek V3.2 |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.2 | Qwen3.5-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
Qwen3.5-Flash costs less
Repository review
50K input + 3K output tokens
Qwen3.5-Flash costs less
Agent loop
200K input + 10K output tokens
Qwen3.5-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 | DeepSeek V3.2 | Qwen3.5-Flash |
|---|---|---|
| Maker | DeepSeek | Qwen |
| Weights | Open weights | No public weights listed |
| Released | December 1, 2025 | February 25, 2026 |
| Context window | 164K | 1M |
| Input $/Mtok | $0.28 | $0.065 |
| Output $/Mtok | $0.42 | $0.26 |
| Coding index | 54.4 | 6.2 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $0.99 | $0.40 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than Qwen3.5-Flash for coding?
Pick DeepSeek V3.2 for coding: it scores 54.4 on the Vibe Coding Index against 6.2 for Qwen3.5-Flash. Pick Qwen3.5-Flash when output tokens cost 1.6x less, or when a solved task costs $0.40 against $0.99.
Which is cheaper, DeepSeek V3.2 or Qwen3.5-Flash?
DeepSeek V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens; Qwen3.5-Flash costs $0.065 and $0.26. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and Qwen3.5-Flash $0.40.
Which has the bigger context window, DeepSeek V3.2 or Qwen3.5-Flash?
Qwen3.5-Flash, with 1M tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs Qwen3.5-Flash comparison based on?
43 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 2 independent benchmarks and Qwen3.5-Flash's on 1. Where only one model has a result, the page says so instead of naming a winner.