Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs Llama 4 Scout

DeepSeek V3.2 leads Llama 4 Scout on the Artificial Analysis Intelligence Index, 21.5 to 6.5, and Llama 4 Scout costs 1.8x less per output token ($0.50 vs $0.88 per million). Updated October 22, 2026; 60 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace Llama 4 Scout
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
59
Llama 4 ScoutMeta Llama
Coding
No data
Overall
24.9
Output $/M
$0.50
1
vs boards won of 60 shared

DeepSeek V3.2 or Llama 4 Scout: which to pick

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Llama 4 Scout has none, so the two cannot be ranked on coding.

Pick Llama 4 Scout for output tokens 1.8x cheaper ($0.50 vs $0.88 per million) and a larger context window (1.31M against 164K tokens).

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BLlama 4 ScoutMeta LlamaNot benchmarkedNo coding benchmark$1.276 per solved task
Shared results
60
DeepSeek V3.2 only
15
Llama 4 Scout only
22
Like-for-like categories
8 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.

At a glance

Coding index
DeepSeek V3.2 30.0 from 3 benchmarks, Llama 4 Scout not benchmarked.
Widest category
Agentic work, 75.1 points apart on average over 1 shared benchmark.
Widest single gap
AA Math Index: DeepSeek V3.2 92.0 against Llama 4 Scout 14.0, 78.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against Llama 4 Scout $0.50 per million output tokens, 1.8x apart.
Context window
DeepSeek V3.2 takes 164K tokens, Llama 4 Scout 1.31M.

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.

Boards won, where both have a result
CategoryDeepSeek V3.2BarsLlama 4 ScoutTies
Coding70
Intelligence20
Agentic work10
Reasoning80
Math51
Knowledge100
Web design50
General210
All shared boards591
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for DeepSeek V3.2 and Llama 4 Scout
BenchmarkDeepSeek V3.2Llama 4 ScoutLeader
SWE-bench Verified70.0%9.1%DeepSeek V3.2
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev1362Not measuredOnly DeepSeek V3.2 measured
AA Coding Index44.28.2DeepSeek V3.2
LiveCodeBench (Vals AI)80.7%38.5%DeepSeek V3.2
SWE-bench Verified (Vals AI)67.6%Not measuredOnly DeepSeek V3.2 measured
Vibe Code Bench (Vals AI)5.1%Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Artificial Analysis run)86.2%29.9%DeepSeek V3.2
SciCodeNot measured21.3%Only Llama 4 Scout measured
Terminal-Bench Hard (Artificial Analysis run)35.6%1.5%DeepSeek V3.2
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: coding14531286DeepSeek V3.2
LMArena Text: software and IT14491286DeepSeek V3.2
LMArena WebDev: React1350Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev: HTML1371Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V3.2 and Llama 4 Scout
BenchmarkDeepSeek V3.2Llama 4 ScoutLeader
AA Intelligence Index21.56.5DeepSeek V3.2
Epoch Capabilities Index146.1129.6DeepSeek V3.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.2 and Llama 4 Scout
BenchmarkDeepSeek V3.2Llama 4 ScoutLeader
AA Agentic IndexNot measured0.5Only Llama 4 Scout measured
τ²-Bench Telecom90.6%15.5%DeepSeek V3.2
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
Vending-Bench 2$1,034Not measuredOnly DeepSeek V3.2 measured
Berkeley Function Calling Leaderboard (BFCL)Not measured28.1%Only Llama 4 Scout measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
Reasoning benchmarks for DeepSeek V3.2 and Llama 4 Scout
BenchmarkDeepSeek V3.2Llama 4 ScoutLeader
GPQA Diamond80.3%47.0%DeepSeek V3.2
MMMU Pro (Vals AI)Not measured58.8%Only Llama 4 Scout measured
GPQA Diamond (Artificial Analysis run)84.0%58.7%DeepSeek V3.2
Humanity's Last Exam (Artificial Analysis run)24.6%3.8%DeepSeek V3.2
GPQA Diamond (Epoch AI run)Not measured51.8%Only Llama 4 Scout measured
ARC-AGI57.0%0.5%DeepSeek V3.2
ARC-AGI-24.0%0.0%DeepSeek V3.2
LMArena Text: hard prompts14341266DeepSeek V3.2
LMArena Text: expert14361235DeepSeek V3.2
LMArena Text: hard prompts in English14461293DeepSeek V3.2
LMArena Vision: diagramsNot measured1125Only Llama 4 Scout measured
LMArena Vision: homeworkNot measured1148Only Llama 4 Scout measured
Kagi LLM BenchmarkNot measured36.9%Only Llama 4 Scout measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index51
Math benchmarks for DeepSeek V3.2 and Llama 4 Scout
BenchmarkDeepSeek V3.2Llama 4 ScoutLeader
AIME84.6%19.0%DeepSeek V3.2
MATH 500 (Vals AI)Not measured79.2%Only Llama 4 Scout measured
MGSM (Vals AI)86.0%88.0%Llama 4 Scout
AA Math Index92.014.0DeepSeek V3.2
AIME 2025 (Artificial Analysis run)92.0%14.0%DeepSeek V3.2
OTIS Mock AIMENot measured7.8%Only Llama 4 Scout measured
MATH level 5Not measured62.3%Only Llama 4 Scout measured
LMArena Text: math14351287DeepSeek V3.2
LMArena Text: mathematical work14401286DeepSeek V3.2
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
Knowledge benchmarks for DeepSeek V3.2 and Llama 4 Scout
BenchmarkDeepSeek V3.2Llama 4 ScoutLeader
MMLU Pro84.9%69.6%DeepSeek V3.2
LegalBench (Vals AI)76.1%72.0%DeepSeek V3.2
CaseLaw (Vals AI)55.4%Not measuredOnly DeepSeek V3.2 measured
CorpFin (Vals AI)51.0%46.8%DeepSeek V3.2
TaxEval (Vals AI)68.2%55.2%DeepSeek V3.2
MortgageTax (Vals AI)Not measured57.8%Only Llama 4 Scout measured
MedQA (Vals AI)93.9%50.9%DeepSeek V3.2
MedCode (Vals AI)Not measured23.3%Only Llama 4 Scout measured
MMLU Pro (Artificial Analysis run)86.2%75.2%DeepSeek V3.2
LMArena Text: science14461278DeepSeek V3.2
LMArena Text: medicine and healthcare14401275DeepSeek V3.2
LMArena Text: legal and government14251285DeepSeek V3.2
LMArena Text: business and finance14101257DeepSeek V3.2
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index50
Web design benchmarks for DeepSeek V3.2 and Llama 4 Scout
BenchmarkDeepSeek V3.2Llama 4 ScoutLeader
Design Arena: websites1175750DeepSeek V3.2
Design Arena: UI components1146765DeepSeek V3.2
Design Arena: game dev1131772DeepSeek V3.2
Design Arena: data viz1158896DeepSeek V3.2
Design Arena: 3D1132Not measuredOnly DeepSeek V3.2 measured
Design Arena: all code categories1163789DeepSeek V3.2
Design Arena: SVG1032Not measuredOnly DeepSeek V3.2 measured
Design Arena: ASCII art1083Not measuredOnly 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 index210
General benchmarks for DeepSeek V3.2 and Llama 4 Scout
BenchmarkDeepSeek V3.2Llama 4 ScoutLeader
SAGE (Vals AI)Not measured34.8%Only Llama 4 Scout measured
MedScribe (Vals AI)Not measured50.6%Only Llama 4 Scout measured
IFBench60.7%39.5%DeepSeek V3.2
Long context reasoning (AA-LCR)73.3%27.7%DeepSeek V3.2
DTBench85.6%57.9%DeepSeek V3.2
LMCA28.8%12.0%DeepSeek V3.2
Fiction.LiveBenchNot measured36.0%Only Llama 4 Scout measured
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251279DeepSeek V3.2
LMArena Text: instruction following14131248DeepSeek V3.2
LMArena Text: creative writing14001249DeepSeek V3.2
LMArena VisionNot measured1118Only Llama 4 Scout measured
LMArena Text: English14391304DeepSeek V3.2
LMArena Text: non-English14091252DeepSeek V3.2
LMArena Text: Chinese14551255DeepSeek V3.2
LMArena Text: German14131273DeepSeek V3.2
LMArena Text: Japanese13741206DeepSeek V3.2
LMArena Text: Korean13701207DeepSeek V3.2
LMArena Text: French14291283DeepSeek V3.2
LMArena Text: Spanish14241278DeepSeek V3.2
LMArena Text: Russian14241263DeepSeek V3.2
LMArena Text: Polish14191265DeepSeek V3.2
LMArena Text: multi-turn14271280DeepSeek V3.2
LMArena Text: longer queries14281265DeepSeek V3.2
LMArena Text: writing and language14071269DeepSeek V3.2
LMArena Text: entertainment and media13951242DeepSeek V3.2
LMArena Vision: EnglishNot measured1143Only Llama 4 Scout measured
LMArena Vision: ChineseNot measured1106Only Llama 4 Scout measured
LMArena Vision: reading textNot measured1117Only Llama 4 Scout measured
LMArena Vision: humorNot measured1102Only Llama 4 Scout measured
LMArena Vision: creative writingNot measured1126Only Llama 4 Scout measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.2 and Llama 4 Scout
BenchmarkDeepSeek V3.2Llama 4 ScoutLeader
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 V3.2$0.0007Fits in one request
Llama 4 Scout$0.0004Fits in one request

Llama 4 Scout costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
Llama 4 Scout$0.010Fits in one request

Llama 4 Scout costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
Llama 4 Scout$0.040Fits in one request

Llama 4 Scout 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.

Specifications of DeepSeek V3.2 and Llama 4 Scout
SpecificationDeepSeek V3.2Meta Llama 4 Scout
MakerDeepSeekMeta Llama
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025April 5, 2025
Context window164K1.31M
Input $/Mtok$0.29$0.175
Output $/Mtok$0.88$0.50
Coding index30.0Not benchmarked
Independent measurements behind it30
Cost per solved task$0.99$1.276
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than Llama 4 Scout for coding?

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Llama 4 Scout has none, so the two cannot be ranked on coding. Pick Llama 4 Scout for output tokens 1.8x cheaper ($0.50 vs $0.88 per million) and a larger context window (1.31M against 164K tokens).

Which is cheaper, DeepSeek V3.2 or Llama 4 Scout?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Llama 4 Scout costs $0.175 and $0.50. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and Llama 4 Scout $1.276.

Which has the bigger context window, DeepSeek V3.2 or Llama 4 Scout?

Llama 4 Scout, with 1.31M tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs Llama 4 Scout comparison based on?

60 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and Llama 4 Scout's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next