DeepSeek V4.1 Flash vs DeepSeek V4 Pro 0813
Updated October 21, 2026. 66 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 for coding: it scores 77.2 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.
Pick DeepSeek V4 Pro 0813 when what matters is IOI (Vals AI) or Vibe Code Bench 1-100 (Vals AI), where it leads.
- Shared results
- 66
- DeepSeek V4.1 Flash only
- 35
- DeepSeek V4 Pro 0813 only
- 12
- Like-for-like categories
- 7 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
DeepSeek V4.1 Flash scores 77.2 against 54.6.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 leads, 36.0 against 24.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Pro 0813 has a AA Agentic Index result, 41.3.
Directional only
Reasoning
GPQA Diamond
No call
Only DeepSeek V4 Pro 0813 has a GPQA Diamond result, 92.4%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V4 Pro 0813 has a MMLU Pro result, 87.0%.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V4.1 Flash has a Design Arena: websites result, 1309.
Directional only
General
Vals Index
No call
Only DeepSeek V4 Pro 0813 has a Vals Index result, 53.0%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash $0.0003, DeepSeek V4 Pro 0813 $0.0016 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V4 Pro 0813 has the number, $0.10.
Directional only
At a glance
- Coding index
- DeepSeek V4.1 Flash 77.2 from 2 benchmarks, DeepSeek V4 Pro 0813 54.6 from 1 benchmark.
- Widest category
- Coding, 6.6 points apart on average over 17 shared benchmarks.
- Widest single gap
- Terminal-Bench 2.1 (Vals AI): DeepSeek V4.1 Flash 74.5% against DeepSeek V4 Pro 0813 54.7%, 19.9 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4.1 Flash $0.525 against DeepSeek V4 Pro 0813 $1.98 per million output tokens, 3.8x apart.
- Context window
- Both take 1.05M tokens.
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 V4.1 Flash | Bars | DeepSeek V4 Pro 0813 | Ties |
|---|---|---|---|---|
| Coding | 14 | 3 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 3 | 4 | ||
| Reasoning | 6 | 2 | 1 tie | |
| Math | 4 | 1 | 1 tie | |
| Knowledge | 4 | 3 | ||
| General | 15 | 3 | ||
| All shared boards | 47 | 17 | 2 ties |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index143
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Pro 0813 | Leader |
|---|---|---|---|
| LiveBench coding | 90.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena WebDev | 1618 | 1582 | DeepSeek V4.1 Flash |
| AA Coding Index | Not measured | 68.8 | Only DeepSeek V4 Pro 0813 measured |
| LiveCodeBench (Vals AI) | Not measured | 87.5% | Only DeepSeek V4 Pro 0813 measured |
| SWE-bench Verified (Vals AI) | Not measured | 96.4% | Only DeepSeek V4 Pro 0813 measured |
| Terminal-Bench 4 (Vals AI) | 19.7% | 14.1% | DeepSeek V4.1 Flash |
| Vibe Code Bench (Vals AI) | 84.7% | 82.3% | DeepSeek V4.1 Flash |
| Code migration (Vals AI) | 45.6% | 41.5% | DeepSeek V4.1 Flash |
| ProgramBench (Vals AI) | 0.5% | 0.0% | DeepSeek V4.1 Flash |
| IOI (Vals AI) | 40.3% | 51.6% | DeepSeek V4 Pro 0813 |
| Terminal-Bench 2.1 (Vals AI) | 74.5% | 54.7% | DeepSeek V4.1 Flash |
| SWE-bench Multimodal (Vals AI) | 46.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Vibe Code Bench 1-100 (Vals AI) | 16.4% | 17.5% | DeepSeek V4 Pro 0813 |
| SkillsBench (Vals AI) | 69.8% | 53.8% | DeepSeek V4.1 Flash |
| CyberBench (Vals AI) | 73.7% | 72.9% | DeepSeek V4.1 Flash |
| SciCode | 51.9% | 51.0% | DeepSeek V4.1 Flash |
| FrontierCode | 43.9% | 28.5% | DeepSeek V4.1 Flash |
| WeirdML | Not measured | 66.2% | Only DeepSeek V4 Pro 0813 measured |
| ALE-Bench | 1092.3 | 1403.2 | DeepSeek V4 Pro 0813 |
| LMArena Text: coding | 1502 | 1469 | DeepSeek V4.1 Flash |
| LMArena Text: software and IT | 1496 | 1462 | DeepSeek V4.1 Flash |
| LMArena WebDev: React | 1628 | 1588 | DeepSeek V4.1 Flash |
| LMArena WebDev: HTML | 1612 | 1566 | DeepSeek V4.1 Flash |
| LMArena WebDev: from an image | 1606 | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Pro 0813 | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.7 | 36.0 | DeepSeek V4 Pro 0813 |
| Epoch Capabilities Index | 155.9 | 155.6 | DeepSeek V4.1 Flash |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index34
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Pro 0813 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 41.3 | Only DeepSeek V4 Pro 0813 measured |
| LiveBench research | 86.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| LiveBench browser | 84.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| LiveBench long agentic | 40.1% | Not measured | Only DeepSeek V4.1 Flash measured |
| SREBench (Vals AI) | 0.8% | 1.9% | DeepSeek V4 Pro 0813 |
| Finance Agent (Vals AI) | 53.5% | 50.4% | DeepSeek V4.1 Flash |
| Tax Agent Bench (Vals AI) | 26.6% | 26.8% | DeepSeek V4 Pro 0813 |
| Legal Research Bench (Vals AI) | 41.4% | 40.9% | DeepSeek V4.1 Flash |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 10.8% | Only DeepSeek V4 Pro 0813 measured |
| Excel Modeling Benchmark (Vals AI) | 57.2% | 52.8% | DeepSeek V4.1 Flash |
| BioMysteryBench (Vals AI) | 67.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| Terminal-Bench-Science (Vals AI) | 0.0% | 4.3% | DeepSeek V4 Pro 0813 |
| Vals Science Index | 29.6% | Not measured | Only DeepSeek V4.1 Flash measured |
| APEX-Agents | 39.5% | 47.3% | DeepSeek V4 Pro 0813 |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index62
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Pro 0813 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 92.4% | Only DeepSeek V4 Pro 0813 measured |
| LiveBench reasoning | 86.7% | Not measured | Only DeepSeek V4.1 Flash measured |
| MysteryMechanism (Vals AI) | 21.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 92.8% | Only DeepSeek V4 Pro 0813 measured |
| Humanity's Last Exam (Artificial Analysis run) | 39.2% | 41.0% | DeepSeek V4 Pro 0813 |
| GPQA Diamond (Epoch AI run) | 89.8% | 91.7% | DeepSeek V4 Pro 0813 |
| ARC-AGI | 94.5% | 90.5% | DeepSeek V4.1 Flash |
| ARC-AGI-2 | 72.9% | 61.3% | DeepSeek V4.1 Flash |
| Chess puzzles | 48.0% | 46.0% | DeepSeek V4.1 Flash |
| Mystery game puzzles | 43.0% | 43.0% | Tie |
| LMArena Text: hard prompts | 1483 | 1458 | DeepSeek V4.1 Flash |
| LMArena Text: expert | 1501 | 1459 | DeepSeek V4.1 Flash |
| LMArena Text: hard prompts in English | 1488 | 1463 | DeepSeek V4.1 Flash |
| LMArena Vision: diagrams | 1297 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: homework | 1307 | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Pro 0813 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.3% | 98.6% | DeepSeek V4 Pro 0813 |
| FrontierMath, tiers 1 to 3 | 67.4% | 64.6% | DeepSeek V4.1 Flash |
| FrontierMath, tier 4 | 26.8% | 26.8% | Tie |
| ProofBench | 54.0% | 50.0% | DeepSeek V4.1 Flash |
| LMArena Text: math | 1478 | 1441 | DeepSeek V4.1 Flash |
| LMArena Text: mathematical work | 1485 | 1443 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index43
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Pro 0813 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 87.0% | Only DeepSeek V4 Pro 0813 measured |
| LegalBench (Vals AI) | 83.3% | 82.4% | DeepSeek V4.1 Flash |
| CorpFin (Vals AI) | Not measured | 65.4% | Only DeepSeek V4 Pro 0813 measured |
| TaxEval (Vals AI) | Not measured | 73.1% | Only DeepSeek V4 Pro 0813 measured |
| MedCode (Vals AI) | 41.2% | 42.5% | DeepSeek V4 Pro 0813 |
| SimpleQA Verified | 42.9% | 52.9% | DeepSeek V4 Pro 0813 |
| LMArena Text: science | 1469 | 1457 | DeepSeek V4.1 Flash |
| LMArena Text: medicine and healthcare | 1484 | 1446 | DeepSeek V4.1 Flash |
| LMArena Text: legal and government | 1443 | 1459 | DeepSeek V4 Pro 0813 |
| LMArena Text: business and finance | 1461 | 1442 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Pro 0813 | Leader |
|---|---|---|---|
| Design Arena: websites | 1309 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: UI components | 1314 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: game dev | 1331 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: data viz | 1290 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: 3D | 1356 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: all code categories | 1320 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: SVG | 1243 | Not measured | Only DeepSeek V4.1 Flash measured |
| Design Arena: ASCII art | 1265 | Not measured | Only DeepSeek V4.1 Flash measured |
| LiveBench design | 79.2% | Not measured | Only DeepSeek V4.1 Flash measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index153
| Benchmark | DeepSeek V4.1 Flash | DeepSeek V4 Pro 0813 | Leader |
|---|---|---|---|
| Vals Index | Not measured | 53.0% | Only DeepSeek V4 Pro 0813 measured |
| LiveBench data analysis | 79.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| Public Benefits Bench (Vals AI) | 64.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| SAGE (Vals AI) | 47.9% | Not measured | Only DeepSeek V4.1 Flash measured |
| MedScribe (Vals AI) | 85.5% | 80.2% | DeepSeek V4.1 Flash |
| Long context reasoning (AA-LCR) | 84.0% | 80.3% | DeepSeek V4.1 Flash |
| DTBench | 89.9% | 93.9% | DeepSeek V4 Pro 0813 |
| LMCA | 47.0% | 45.5% | DeepSeek V4.1 Flash |
| Surface Evolver Bench | 46.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| Furniture assembly | 34.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text | 1464 | 1446 | DeepSeek V4.1 Flash |
| LMArena Text: instruction following | 1473 | 1448 | DeepSeek V4.1 Flash |
| LMArena Text: creative writing | 1437 | 1439 | DeepSeek V4 Pro 0813 |
| LMArena Vision | 1278 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: English | 1473 | 1457 | DeepSeek V4.1 Flash |
| LMArena Text: non-English | 1449 | 1431 | DeepSeek V4.1 Flash |
| LMArena Text: Chinese | 1501 | 1481 | DeepSeek V4.1 Flash |
| LMArena Text: German | 1470 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: Japanese | 1432 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: Korean | 1436 | 1449 | DeepSeek V4 Pro 0813 |
| LMArena Text: French | 1465 | 1446 | DeepSeek V4.1 Flash |
| LMArena Text: Spanish | 1459 | 1435 | DeepSeek V4.1 Flash |
| LMArena Text: Russian | 1467 | 1448 | DeepSeek V4.1 Flash |
| LMArena Text: Polish | 1457 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: multi-turn | 1461 | 1454 | DeepSeek V4.1 Flash |
| LMArena Text: longer queries | 1473 | 1458 | DeepSeek V4.1 Flash |
| LMArena Text: writing and language | 1450 | 1443 | DeepSeek V4.1 Flash |
| LMArena Text: entertainment and media | 1445 | 1424 | DeepSeek V4.1 Flash |
| LMArena Vision: English | 1288 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: Chinese | 1327 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: reading text | 1282 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: humor | 1260 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Vision: creative writing | 1275 | Not measured | Only DeepSeek V4.1 Flash measured |
| 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 | DeepSeek V4.1 Flash | DeepSeek V4 Pro 0813 | 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 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4.1 Flash costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4.1 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 V4.1 Flash | DeepSeek V4 Pro 0813 |
|---|---|---|
| Maker | DeepSeek | DeepSeek |
| Weights | Open weights | Open weights |
| Released | September 10, 2026 | August 12, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.049 | $0.66 |
| Output $/Mtok | $0.525 | $1.98 |
| Coding index | 77.2 | 54.6 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | Not computable | $0.10 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4.1 Flash better than DeepSeek V4 Pro 0813 for coding?
Pick DeepSeek V4.1 Flash for coding: it scores 77.2 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when what matters is IOI (Vals AI) or Vibe Code Bench 1-100 (Vals AI), where it leads.
Which is cheaper, DeepSeek V4.1 Flash or DeepSeek V4 Pro 0813?
DeepSeek V4.1 Flash costs $0.049 per million input tokens and $0.525 per million output tokens; DeepSeek V4 Pro 0813 costs $0.66 and $1.98. Cost per solved task is known for DeepSeek V4 Pro 0813 only.
Which has the bigger context window, DeepSeek V4.1 Flash or DeepSeek V4 Pro 0813?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4.1 Flash vs DeepSeek V4 Pro 0813 comparison based on?
66 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4.1 Flash's coding index rests on 2 independent benchmarks and DeepSeek V4 Pro 0813's on 1. Where only one model has a result, the page says so instead of naming a winner.