DeepSeek V3.2 vs DeepSeek V4.1 Flash 1017
Updated October 21, 2026. 14 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 V4.1 Flash 1017 for coding: it scores 83.3 on the Vibe Coding Index against 54.4 for DeepSeek V3.2.
Pick DeepSeek V3.2 when output tokens cost 1.4x less.
- Shared results
- 14
- DeepSeek V3.2 only
- 61
- DeepSeek V4.1 Flash 1017 only
- 18
- Like-for-like categories
- 5 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 V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 scores 83.3 against 54.4.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 leads, 39.5 against 21.5.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only DeepSeek V3.2 has a GPQA Diamond result, 80.3%.
Directional only
Math
AIME
No call
Only DeepSeek V3.2 has a AIME result, 84.6%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V3.2 has a MMLU Pro result, 84.9%.
Directional only
Web design
Design Arena: websites
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 leads, 1312 against 1175.
Same board, both measured
General
Vals Index
No call
Only DeepSeek V4.1 Flash 1017 has a Vals Index result, 61.3%.
Directional only
Long documents
Listed context window
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4.1 Flash 1017
DeepSeek V3.2 $0.0005, DeepSeek V4.1 Flash 1017 $0.0004 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V3.2 has the number, $0.99.
Directional only
At a glance
- Coding index
- DeepSeek V3.2 54.4 from 2 benchmarks, DeepSeek V4.1 Flash 1017 83.3 from 2 benchmarks.
- Widest category
- Coding, 51.4 points apart on average over 4 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V3.2 5.1% against DeepSeek V4.1 Flash 1017 87.7%, 82.6 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.42 against DeepSeek V4.1 Flash 1017 $0.60 per million output tokens, 1.4x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, DeepSeek V4.1 Flash 1017 1.05M.
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 | DeepSeek V4.1 Flash 1017 | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 1 | ||
| Web design | 0 | 7 | ||
| General | 0 | 1 | ||
| All shared boards | 0 | 14 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index04
| Benchmark | DeepSeek V3.2 | DeepSeek V4.1 Flash 1017 | 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 |
| LiveBench coding | Not measured | 96.0% | Only DeepSeek V4.1 Flash 1017 measured |
| LMArena WebDev | 1362 | 1664 | DeepSeek V4.1 Flash 1017 |
| AA Coding Index | 44.2 | Not measured | Only DeepSeek V3.2 measured |
| LiveCodeBench (Vals AI) | 80.7% | Not measured | Only DeepSeek V3.2 measured |
| SWE-bench Verified (Vals AI) | 67.6% | Not measured | Only DeepSeek V3.2 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 31.8% | Only DeepSeek V4.1 Flash 1017 measured |
| Vibe Code Bench (Vals AI) | 5.1% | 87.7% | DeepSeek V4.1 Flash 1017 |
| Code migration (Vals AI) | Not measured | 44.2% | Only DeepSeek V4.1 Flash 1017 measured |
| LiveCodeBench (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SciCode | Not measured | 55.9% | Only DeepSeek V4.1 Flash 1017 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 | 1622.0 | Only DeepSeek V4.1 Flash 1017 measured |
| LMArena Text: coding | 1453 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: software and IT | 1449 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: React | 1350 | 1667 | DeepSeek V4.1 Flash 1017 |
| LMArena WebDev: HTML | 1371 | 1687 | DeepSeek V4.1 Flash 1017 |
| Neither model has a result on the other 19 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | DeepSeek V4.1 Flash 1017 | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | 39.5 | DeepSeek V4.1 Flash 1017 |
| Epoch Capabilities Index | 146.1 | Not measured | Only DeepSeek V3.2 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
| Benchmark | DeepSeek V3.2 | DeepSeek V4.1 Flash 1017 | Leader |
|---|---|---|---|
| Design Arena: spreadsheets | Not measured | 1238 | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench research | Not measured | 79.5% | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench browser | Not measured | 76.0% | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench long agentic | Not measured | 50.9% | Only DeepSeek V4.1 Flash 1017 measured |
| Finance Agent (Vals AI) | Not measured | 57.0% | Only DeepSeek V4.1 Flash 1017 measured |
| Tax Agent Bench (Vals AI) | Not measured | 44.4% | Only DeepSeek V4.1 Flash 1017 measured |
| Legal Research Bench (Vals AI) | Not measured | 45.2% | Only DeepSeek V4.1 Flash 1017 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 14.2% | Only DeepSeek V4.1 Flash 1017 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 61.8% | Only DeepSeek V4.1 Flash 1017 measured |
| 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 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | DeepSeek V4.1 Flash 1017 | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | Not measured | Only DeepSeek V3.2 measured |
| LiveBench reasoning | Not measured | 89.1% | Only DeepSeek V4.1 Flash 1017 measured |
| GPQA Diamond (Artificial Analysis run) | 84.0% | Not measured | Only DeepSeek V3.2 measured |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | 43.3% | DeepSeek V4.1 Flash 1017 |
| ARC-AGI | 57.0% | Not measured | Only DeepSeek V3.2 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts | 1434 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: expert | 1436 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts in English | 1446 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 12 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V3.2 | DeepSeek V4.1 Flash 1017 | Leader |
|---|---|---|---|
| AIME | 84.6% | Not measured | Only DeepSeek V3.2 measured |
| 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 |
| LMArena Text: math | 1435 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: mathematical work | 1440 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | DeepSeek V3.2 | DeepSeek V4.1 Flash 1017 | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | Not measured | Only DeepSeek V3.2 measured |
| LegalBench (Vals AI) | 76.1% | Not measured | Only DeepSeek V3.2 measured |
| CaseLaw (Vals AI) | 55.4% | Not measured | Only DeepSeek V3.2 measured |
| CorpFin (Vals AI) | 51.0% | Not measured | Only DeepSeek V3.2 measured |
| TaxEval (Vals AI) | 68.2% | Not measured | Only DeepSeek V3.2 measured |
| MedQA (Vals AI) | 93.9% | Not measured | Only DeepSeek V3.2 measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: science | 1446 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: medicine and healthcare | 1440 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: legal and government | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: business and finance | 1410 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | DeepSeek V3.2 | DeepSeek V4.1 Flash 1017 | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | 1312 | DeepSeek V4.1 Flash 1017 |
| Design Arena: UI components | 1149 | 1305 | DeepSeek V4.1 Flash 1017 |
| Design Arena: game dev | 1132 | 1365 | DeepSeek V4.1 Flash 1017 |
| Design Arena: data viz | 1158 | 1330 | DeepSeek V4.1 Flash 1017 |
| Design Arena: 3D | 1133 | 1368 | DeepSeek V4.1 Flash 1017 |
| Design Arena: all code categories | 1164 | 1335 | DeepSeek V4.1 Flash 1017 |
| Design Arena: SVG | 1032 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: ASCII art | 1082 | 1244 | DeepSeek V4.1 Flash 1017 |
| LiveBench design | Not measured | 83.4% | Only DeepSeek V4.1 Flash 1017 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | DeepSeek V4.1 Flash 1017 | Leader |
|---|---|---|---|
| Vals Index | Not measured | 61.3% | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench data analysis | Not measured | 79.5% | Only DeepSeek V4.1 Flash 1017 measured |
| IFBench | 60.7% | Not measured | Only DeepSeek V3.2 measured |
| Long context reasoning (AA-LCR) | 73.3% | 82.7% | DeepSeek V4.1 Flash 1017 |
| DTBench | 85.6% | Not measured | Only DeepSeek V3.2 measured |
| LMCA | 28.8% | Not measured | Only DeepSeek V3.2 measured |
| 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 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: instruction following | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: creative writing | 1400 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: English | 1439 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: non-English | 1409 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Chinese | 1455 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: German | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Japanese | 1374 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Korean | 1370 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: French | 1429 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Spanish | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Russian | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Polish | 1419 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: multi-turn | 1427 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: longer queries | 1428 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: writing and language | 1407 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: entertainment and media | 1395 | Not measured | Only DeepSeek V3.2 measured |
| 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 | DeepSeek V4.1 Flash 1017 | 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
DeepSeek V4.1 Flash 1017 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4.1 Flash 1017 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4.1 Flash 1017 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 | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| Maker | DeepSeek | DeepSeek |
| Weights | Open weights | Open weights |
| Released | December 1, 2025 | October 17, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.28 | $0.15 |
| Output $/Mtok | $0.42 | $0.60 |
| Coding index | 54.4 | 83.3 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $0.99 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than DeepSeek V4.1 Flash 1017 for coding?
Pick DeepSeek V4.1 Flash 1017 for coding: it scores 83.3 on the Vibe Coding Index against 54.4 for DeepSeek V3.2. Pick DeepSeek V3.2 when output tokens cost 1.4x less.
Which is cheaper, DeepSeek V3.2 or DeepSeek V4.1 Flash 1017?
DeepSeek V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens; DeepSeek V4.1 Flash 1017 costs $0.15 and $0.60. Cost per solved task is known for DeepSeek V3.2 only.
Which has the bigger context window, DeepSeek V3.2 or DeepSeek V4.1 Flash 1017?
DeepSeek V4.1 Flash 1017, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs DeepSeek V4.1 Flash 1017 comparison based on?
14 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 2 independent benchmarks and DeepSeek V4.1 Flash 1017's on 2. Where only one model has a result, the page says so instead of naming a winner.