DeepSeek V3.2 Exp vs DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423 leads DeepSeek V3.2 Exp on the Artificial Analysis Intelligence Index, 24.4 to 16.6, and DeepSeek V4 Flash 0423 costs 1.5x less per output token ($0.28 vs $0.41 per million). Updated October 22, 2026; 43 benchmarks have a result for both.
DeepSeek V3.2 Exp or DeepSeek V4 Flash 0423: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick DeepSeek V3.2 Exp for work measured by LMArena WebDev or WeirdML, where it leads.
- Shared results
- 43
- DeepSeek V3.2 Exp only
- 16
- DeepSeek V4 Flash 0423 only
- 6
- Like-for-like categories
- 7 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
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423 leads, 24.4 against 16.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Flash 0423 has a AA Agentic Index result, 26.3.
Directional only
Web design
Design Arena: websites
DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423 leads, 1207 against 1178.
Same board, both measured
Long documents
Listed context window
DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423 takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0423
DeepSeek V3.2 Exp $0.0005, DeepSeek V4 Flash 0423 $0.0003 per turn.
List prices
At a glance
- Coding index
- DeepSeek V3.2 Exp not benchmarked, DeepSeek V4 Flash 0423 not benchmarked.
- Widest category
- Coding, 20.4 points apart on average over 5 shared benchmarks.
- Widest single gap
- LMArena WebDev: HTML: DeepSeek V3.2 Exp 1281 against DeepSeek V4 Flash 0423 1558, 46.1 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 Exp $0.41 against DeepSeek V4 Flash 0423 $0.28 per million output tokens, 1.5x apart.
- Context window
- DeepSeek V3.2 Exp takes 164K tokens, DeepSeek V4 Flash 0423 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 Exp | Bars | DeepSeek V4 Flash 0423 | Ties |
|---|---|---|---|---|
| Coding | 0 | 5 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 3 | 1 tie | |
| Math | 1 | 1 | ||
| Knowledge | 1 | 3 | ||
| Web design | 2 | 5 | ||
| General | 6 | 13 | ||
| All shared boards | 10 | 32 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
| Benchmark | DeepSeek V3.2 Exp | DeepSeek V4 Flash 0423 | Leader |
|---|---|---|---|
| Aider polyglot | 74.2% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena WebDev | 1272 | 1582 | DeepSeek V4 Flash 0423 |
| AA Coding Index | Not measured | 52.0 | Only DeepSeek V4 Flash 0423 measured |
| LiveCodeBench (Artificial Analysis run) | 78.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| Terminal-Bench Hard (Artificial Analysis run) | 31.1% | Not measured | Only DeepSeek V3.2 Exp measured |
| WeirdML | 39.5% | 45.6% | DeepSeek V4 Flash 0423 |
| ALE-Bench | Not measured | 678.2 | Only DeepSeek V4 Flash 0423 measured |
| LMArena Text: coding | 1438 | 1457 | DeepSeek V4 Flash 0423 |
| LMArena Text: software and IT | 1438 | 1453 | DeepSeek V4 Flash 0423 |
| LMArena WebDev: React | Not measured | 1585 | Only DeepSeek V4 Flash 0423 measured |
| LMArena WebDev: HTML | 1281 | 1558 | DeepSeek V4 Flash 0423 |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.2 Exp | DeepSeek V4 Flash 0423 | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.6 | 24.4 | DeepSeek V4 Flash 0423 |
| Epoch Capabilities Index | 144.9 | 146.1 | DeepSeek V4 Flash 0423 |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | DeepSeek V4 Flash 0423 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 26.3 | Only DeepSeek V4 Flash 0423 measured |
| τ²-Bench Telecom | 33.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| TheAgentCompany | 42.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| Berkeley Function Calling Leaderboard (BFCL) | 56.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V3.2 Exp | DeepSeek V4 Flash 0423 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 79.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| Humanity's Last Exam (Artificial Analysis run) | 14.9% | Not measured | Only DeepSeek V3.2 Exp measured |
| SimpleBench | Not measured | 46.3% | Only DeepSeek V4 Flash 0423 measured |
| LMArena Text: hard prompts | 1429 | 1444 | DeepSeek V4 Flash 0423 |
| LMArena Text: expert | 1422 | 1441 | DeepSeek V4 Flash 0423 |
| LMArena Text: hard prompts in English | 1444 | 1449 | DeepSeek V4 Flash 0423 |
| Kagi LLM Benchmark | 52.2% | 52.2% | Tie |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | DeepSeek V3.2 Exp | DeepSeek V4 Flash 0423 | Leader |
|---|---|---|---|
| AA Math Index | 87.7 | Not measured | Only DeepSeek V3.2 Exp measured |
| AIME 2025 (Artificial Analysis run) | 87.7% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: math | 1422 | 1426 | DeepSeek V4 Flash 0423 |
| LMArena Text: mathematical work | 1433 | 1432 | DeepSeek V3.2 Exp |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | DeepSeek V3.2 Exp | DeepSeek V4 Flash 0423 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 85.0% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text: science | 1443 | 1446 | DeepSeek V4 Flash 0423 |
| LMArena Text: medicine and healthcare | 1468 | 1448 | DeepSeek V3.2 Exp |
| LMArena Text: legal and government | 1419 | 1439 | DeepSeek V4 Flash 0423 |
| LMArena Text: business and finance | 1412 | 1425 | DeepSeek V4 Flash 0423 |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index25
| Benchmark | DeepSeek V3.2 Exp | DeepSeek V4 Flash 0423 | Leader |
|---|---|---|---|
| Design Arena: websites | 1178 | 1207 | DeepSeek V4 Flash 0423 |
| Design Arena: UI components | 1164 | 1162 | DeepSeek V3.2 Exp |
| Design Arena: game dev | 1144 | 1196 | DeepSeek V4 Flash 0423 |
| Design Arena: data viz | 1152 | 1127 | DeepSeek V3.2 Exp |
| Design Arena: 3D | 1148 | 1188 | DeepSeek V4 Flash 0423 |
| Design Arena: all code categories | 1170 | 1205 | DeepSeek V4 Flash 0423 |
| Design Arena: SVG | 1031 | 1155 | DeepSeek V4 Flash 0423 |
| Design Arena: ASCII art | Not measured | 1109 | Only DeepSeek V4 Flash 0423 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index613
| Benchmark | DeepSeek V3.2 Exp | DeepSeek V4 Flash 0423 | Leader |
|---|---|---|---|
| IFBench | 54.1% | Not measured | Only DeepSeek V3.2 Exp measured |
| Long context reasoning (AA-LCR) | 72.3% | Not measured | Only DeepSeek V3.2 Exp measured |
| DTBench | 87.7% | 86.4% | DeepSeek V3.2 Exp |
| LMCA | 29.1% | 35.9% | DeepSeek V4 Flash 0423 |
| Fiction.LiveBench | 83.3% | Not measured | Only DeepSeek V3.2 Exp measured |
| CL-bench | 13.2% | Not measured | Only DeepSeek V3.2 Exp measured |
| CL-bench Life | 9.5% | Not measured | Only DeepSeek V3.2 Exp measured |
| LMArena Text | 1425 | 1432 | DeepSeek V4 Flash 0423 |
| LMArena Text: instruction following | 1401 | 1421 | DeepSeek V4 Flash 0423 |
| LMArena Text: creative writing | 1404 | 1403 | DeepSeek V3.2 Exp |
| LMArena Text: English | 1441 | 1441 | DeepSeek V3.2 Exp |
| LMArena Text: non-English | 1404 | 1419 | DeepSeek V4 Flash 0423 |
| LMArena Text: Chinese | 1461 | 1463 | DeepSeek V4 Flash 0423 |
| LMArena Text: German | 1440 | 1419 | DeepSeek V3.2 Exp |
| LMArena Text: Japanese | 1331 | 1389 | DeepSeek V4 Flash 0423 |
| LMArena Text: Korean | 1372 | 1383 | DeepSeek V4 Flash 0423 |
| LMArena Text: French | 1434 | 1439 | DeepSeek V4 Flash 0423 |
| LMArena Text: Spanish | 1441 | 1436 | DeepSeek V3.2 Exp |
| LMArena Text: Russian | 1412 | 1427 | DeepSeek V4 Flash 0423 |
| LMArena Text: Polish | 1435 | 1436 | DeepSeek V4 Flash 0423 |
| LMArena Text: multi-turn | 1422 | 1449 | DeepSeek V4 Flash 0423 |
| LMArena Text: longer queries | 1418 | 1434 | DeepSeek V4 Flash 0423 |
| LMArena Text: writing and language | 1407 | 1410 | DeepSeek V4 Flash 0423 |
| LMArena Text: entertainment and media | 1407 | 1400 | DeepSeek V3.2 Exp |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.2 Exp | DeepSeek V4 Flash 0423 | 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 Flash 0423 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Flash 0423 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Flash 0423 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 Exp | DeepSeek V4 Flash 0423 |
|---|---|---|
| Maker | DeepSeek | DeepSeek |
| Weights | Open weights | Open weights |
| Released | September 29, 2025 | April 24, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.27 | $0.14 |
| Output $/Mtok | $0.41 | $0.28 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 Exp better than DeepSeek V4 Flash 0423 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.2 Exp for work measured by LMArena WebDev or WeirdML, where it leads.
Which is cheaper, DeepSeek V3.2 Exp or DeepSeek V4 Flash 0423?
DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens; DeepSeek V4 Flash 0423 costs $0.14 and $0.28. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V3.2 Exp or DeepSeek V4 Flash 0423?
DeepSeek V4 Flash 0423, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.2 Exp vs DeepSeek V4 Flash 0423 comparison based on?
43 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2 Exp's coding index rests on 1 independent benchmark and DeepSeek V4 Flash 0423's on 1. Where only one model has a result, the page says so instead of naming a winner.