DeepSeek V4.1 Flash vs Llama 4 Maverick
Updated October 21, 2026. 56 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 18.1 for Llama 4 Maverick.
Llama 4 Maverick is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 56
- DeepSeek V4.1 Flash only
- 45
- Llama 4 Maverick only
- 28
- 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 18.1.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash leads, 24.7 against 9.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Llama 4 Maverick has a AA Agentic Index result, 0.6.
Directional only
Reasoning
GPQA Diamond
No call
Only Llama 4 Maverick has a GPQA Diamond result, 69.4%.
Directional only
Math
AIME
No call
Only Llama 4 Maverick has a AIME result, 25.2%.
Directional only
Knowledge
MMLU Pro
No call
Only Llama 4 Maverick has a MMLU Pro result, 79.4%.
Directional only
Web design
Design Arena: websites
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash leads, 1309 against 871.
Same board, both measured
Long documents
Listed context window
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash $0.0003, Llama 4 Maverick $0.0005 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Llama 4 Maverick has the number, $1.491.
Directional only
At a glance
- Coding index
- DeepSeek V4.1 Flash 77.2 from 2 benchmarks, Llama 4 Maverick 18.1 from 2 benchmarks.
- Widest category
- Web design, 55.2 points apart on average over 6 shared benchmarks.
- Widest single gap
- ARC-AGI: DeepSeek V4.1 Flash 94.5% against Llama 4 Maverick 4.4%, 90.1 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4.1 Flash $0.525 against Llama 4 Maverick $0.6525 per million output tokens, 1.2x apart.
- Context window
- DeepSeek V4.1 Flash takes 1.05M tokens, Llama 4 Maverick 524K.
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 | Llama 4 Maverick | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 2 | 0 | ||
| Reasoning | 8 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 6 | 0 | ||
| Web design | 6 | 0 | ||
| General | 28 | 0 | ||
| All shared boards | 56 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index40
| Benchmark | DeepSeek V4.1 Flash | Llama 4 Maverick | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 15.6% | Only Llama 4 Maverick measured |
| SWE-bench Verified | Not measured | 21.0% | Only Llama 4 Maverick measured |
| LiveBench coding | 90.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena WebDev | 1618 | Not measured | Only DeepSeek V4.1 Flash measured |
| AA Coding Index | Not measured | 16.3 | Only Llama 4 Maverick measured |
| LiveCodeBench (Vals AI) | Not measured | 47.3% | Only Llama 4 Maverick measured |
| Terminal-Bench 4 (Vals AI) | 19.7% | Not measured | Only DeepSeek V4.1 Flash measured |
| Vibe Code Bench (Vals AI) | 84.7% | Not measured | Only DeepSeek V4.1 Flash measured |
| Code migration (Vals AI) | 45.6% | Not measured | Only DeepSeek V4.1 Flash measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| IOI (Vals AI) | 40.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| Terminal-Bench 2.1 (Vals AI) | 74.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| SWE-bench Multimodal (Vals AI) | 46.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Vibe Code Bench 1-100 (Vals AI) | 16.4% | Not measured | Only DeepSeek V4.1 Flash measured |
| SkillsBench (Vals AI) | 69.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| CyberBench (Vals AI) | 73.7% | Not measured | Only DeepSeek V4.1 Flash measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 39.7% | Only Llama 4 Maverick measured |
| SciCode | 51.9% | 31.7% | DeepSeek V4.1 Flash |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 6.8% | Only Llama 4 Maverick measured |
| FrontierCode | 43.9% | Not measured | Only DeepSeek V4.1 Flash measured |
| WeirdML | Not measured | 24.5% | Only Llama 4 Maverick measured |
| ALE-Bench | 1092.3 | 173.0 | DeepSeek V4.1 Flash |
| LMArena Text: coding | 1502 | 1301 | DeepSeek V4.1 Flash |
| LMArena Text: software and IT | 1496 | 1299 | DeepSeek V4.1 Flash |
| LMArena WebDev: React | 1628 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena WebDev: HTML | 1612 | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena WebDev: from an image | 1606 | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 11 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4.1 Flash | Llama 4 Maverick | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.7 | 9.3 | DeepSeek V4.1 Flash |
| Epoch Capabilities Index | 155.9 | 132.2 | DeepSeek V4.1 Flash |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
| Benchmark | DeepSeek V4.1 Flash | Llama 4 Maverick | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 0.6 | Only Llama 4 Maverick 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% | Not measured | Only DeepSeek V4.1 Flash measured |
| Finance Agent (Vals AI) | 53.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Tax Agent Bench (Vals AI) | 26.6% | Not measured | Only DeepSeek V4.1 Flash measured |
| Legal Research Bench (Vals AI) | 41.4% | Not measured | Only DeepSeek V4.1 Flash measured |
| Excel Modeling Benchmark (Vals AI) | 57.2% | Not measured | Only DeepSeek V4.1 Flash measured |
| BioMysteryBench (Vals AI) | 67.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| Terminal-Bench-Science (Vals AI) | 0.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| Vals Science Index | 29.6% | Not measured | Only DeepSeek V4.1 Flash measured |
| τ²-Bench Telecom | Not measured | 17.8% | Only Llama 4 Maverick measured |
| APEX-Agents | 39.5% | Not measured | Only DeepSeek V4.1 Flash measured |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | DeepSeek V4.1 Flash | Llama 4 Maverick | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 69.4% | Only Llama 4 Maverick 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 |
| MMMU Pro (Vals AI) | Not measured | 71.7% | Only Llama 4 Maverick measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 67.1% | Only Llama 4 Maverick measured |
| Humanity's Last Exam (Artificial Analysis run) | 39.2% | 4.9% | DeepSeek V4.1 Flash |
| GPQA Diamond (Epoch AI run) | 89.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| ARC-AGI | 94.5% | 4.4% | DeepSeek V4.1 Flash |
| ARC-AGI-2 | 72.9% | 0.0% | DeepSeek V4.1 Flash |
| SimpleBench | Not measured | 27.7% | Only Llama 4 Maverick measured |
| Chess puzzles | 48.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| Mystery game puzzles | 43.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: hard prompts | 1483 | 1281 | DeepSeek V4.1 Flash |
| LMArena Text: expert | 1501 | 1259 | DeepSeek V4.1 Flash |
| LMArena Text: hard prompts in English | 1488 | 1295 | DeepSeek V4.1 Flash |
| LMArena Vision: diagrams | 1297 | 1134 | DeepSeek V4.1 Flash |
| LMArena Vision: homework | 1307 | 1164 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4.1 Flash | Llama 4 Maverick | Leader |
|---|---|---|---|
| AIME | Not measured | 25.2% | Only Llama 4 Maverick measured |
| MATH 500 (Vals AI) | Not measured | 85.2% | Only Llama 4 Maverick measured |
| MGSM (Vals AI) | Not measured | 92.4% | Only Llama 4 Maverick measured |
| AA Math Index | Not measured | 19.3 | Only Llama 4 Maverick measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 19.3% | Only Llama 4 Maverick measured |
| OTIS Mock AIME | 98.3% | Not measured | Only DeepSeek V4.1 Flash measured |
| FrontierMath, tiers 1 to 3 | 67.4% | Not measured | Only DeepSeek V4.1 Flash measured |
| FrontierMath, tier 4 | 26.8% | Not measured | Only DeepSeek V4.1 Flash measured |
| ProofBench | 54.0% | Not measured | Only DeepSeek V4.1 Flash measured |
| LMArena Text: math | 1478 | 1299 | DeepSeek V4.1 Flash |
| LMArena Text: mathematical work | 1485 | 1295 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 2 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | DeepSeek V4.1 Flash | Llama 4 Maverick | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 79.4% | Only Llama 4 Maverick measured |
| LegalBench (Vals AI) | 83.3% | 77.8% | DeepSeek V4.1 Flash |
| CorpFin (Vals AI) | Not measured | 49.7% | Only Llama 4 Maverick measured |
| TaxEval (Vals AI) | Not measured | 66.6% | Only Llama 4 Maverick measured |
| MortgageTax (Vals AI) | Not measured | 58.5% | Only Llama 4 Maverick measured |
| MedQA (Vals AI) | Not measured | 43.3% | Only Llama 4 Maverick measured |
| MedCode (Vals AI) | 41.2% | 36.5% | DeepSeek V4.1 Flash |
| MMLU Pro (Artificial Analysis run) | Not measured | 80.9% | Only Llama 4 Maverick measured |
| SimpleQA Verified | 42.9% | Not measured | Only DeepSeek V4.1 Flash measured |
| GeoBench | Not measured | 52.0% | Only Llama 4 Maverick measured |
| LMArena Text: science | 1469 | 1288 | DeepSeek V4.1 Flash |
| LMArena Text: medicine and healthcare | 1484 | 1275 | DeepSeek V4.1 Flash |
| LMArena Text: legal and government | 1443 | 1286 | DeepSeek V4.1 Flash |
| LMArena Text: business and finance | 1461 | 1260 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | DeepSeek V4.1 Flash | Llama 4 Maverick | Leader |
|---|---|---|---|
| Design Arena: websites | 1309 | 871 | DeepSeek V4.1 Flash |
| Design Arena: UI components | 1314 | 899 | DeepSeek V4.1 Flash |
| Design Arena: game dev | 1331 | 838 | DeepSeek V4.1 Flash |
| Design Arena: data viz | 1290 | 882 | DeepSeek V4.1 Flash |
| Design Arena: 3D | 1356 | 901 | DeepSeek V4.1 Flash |
| Design Arena: all code categories | 1320 | 880 | DeepSeek V4.1 Flash |
| 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 index280
| Benchmark | DeepSeek V4.1 Flash | Llama 4 Maverick | Leader |
|---|---|---|---|
| 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% | 35.7% | DeepSeek V4.1 Flash |
| MedScribe (Vals AI) | 85.5% | 54.2% | DeepSeek V4.1 Flash |
| IFBench | Not measured | 43.0% | Only Llama 4 Maverick measured |
| Long context reasoning (AA-LCR) | 84.0% | 50.0% | DeepSeek V4.1 Flash |
| DTBench | 89.9% | 61.9% | DeepSeek V4.1 Flash |
| LMCA | 47.0% | 15.9% | DeepSeek V4.1 Flash |
| Fiction.LiveBench | Not measured | 46.2% | Only Llama 4 Maverick measured |
| Creative writing (Lech Mazur) | Not measured | 62.0% | Only Llama 4 Maverick measured |
| 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 | 1287 | DeepSeek V4.1 Flash |
| LMArena Text: instruction following | 1473 | 1267 | DeepSeek V4.1 Flash |
| LMArena Text: creative writing | 1437 | 1266 | DeepSeek V4.1 Flash |
| LMArena Vision | 1278 | 1142 | DeepSeek V4.1 Flash |
| LMArena Text: English | 1473 | 1303 | DeepSeek V4.1 Flash |
| LMArena Text: non-English | 1449 | 1269 | DeepSeek V4.1 Flash |
| LMArena Text: Chinese | 1501 | 1277 | DeepSeek V4.1 Flash |
| LMArena Text: German | 1470 | 1291 | DeepSeek V4.1 Flash |
| LMArena Text: Japanese | 1432 | 1206 | DeepSeek V4.1 Flash |
| LMArena Text: Korean | 1436 | 1203 | DeepSeek V4.1 Flash |
| LMArena Text: French | 1465 | 1259 | DeepSeek V4.1 Flash |
| LMArena Text: Spanish | 1459 | 1293 | DeepSeek V4.1 Flash |
| LMArena Text: Russian | 1467 | 1286 | DeepSeek V4.1 Flash |
| LMArena Text: Polish | 1457 | 1275 | DeepSeek V4.1 Flash |
| LMArena Text: multi-turn | 1461 | 1289 | DeepSeek V4.1 Flash |
| LMArena Text: longer queries | 1473 | 1280 | DeepSeek V4.1 Flash |
| LMArena Text: writing and language | 1450 | 1277 | DeepSeek V4.1 Flash |
| LMArena Text: entertainment and media | 1445 | 1250 | DeepSeek V4.1 Flash |
| LMArena Vision: English | 1288 | 1150 | DeepSeek V4.1 Flash |
| LMArena Vision: Chinese | 1327 | 1141 | DeepSeek V4.1 Flash |
| LMArena Vision: reading text | 1282 | 1143 | DeepSeek V4.1 Flash |
| LMArena Vision: humor | 1260 | 1100 | DeepSeek V4.1 Flash |
| LMArena Vision: creative writing | 1275 | 1099 | DeepSeek V4.1 Flash |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4.1 Flash | Llama 4 Maverick | 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 | Meta Llama 4 Maverick |
|---|---|---|
| Maker | DeepSeek | Meta Llama |
| Weights | Open weights | Open weights |
| Released | September 10, 2026 | April 5, 2025 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $0.049 | $0.1875 |
| Output $/Mtok | $0.525 | $0.6525 |
| Coding index | 77.2 | 18.1 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | Not computable | $1.491 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4.1 Flash better than Llama 4 Maverick for coding?
Pick DeepSeek V4.1 Flash for coding: it scores 77.2 on the Vibe Coding Index against 18.1 for Llama 4 Maverick. Llama 4 Maverick is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, DeepSeek V4.1 Flash or Llama 4 Maverick?
DeepSeek V4.1 Flash costs $0.049 per million input tokens and $0.525 per million output tokens; Llama 4 Maverick costs $0.1875 and $0.6525. Cost per solved task is known for Llama 4 Maverick only.
Which has the bigger context window, DeepSeek V4.1 Flash or Llama 4 Maverick?
DeepSeek V4.1 Flash, with 1.05M tokens against 524K.
How many benchmarks is the DeepSeek V4.1 Flash vs Llama 4 Maverick comparison based on?
56 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 Llama 4 Maverick's on 2. Where only one model has a result, the page says so instead of naming a winner.