Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs Llama 4 Scout

gpt-oss-20b leads Llama 4 Scout on the Artificial Analysis Intelligence Index, 10.0 to 6.5, and gpt-oss-20b costs 3.3x less per output token ($0.15 vs $0.50 per million). Updated October 21, 2026; 57 benchmarks have a result for both.

Replace gpt-oss-20b Replace Llama 4 Scout
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
43
Llama 4 ScoutMeta Llama
Coding
No data
Overall
24.9
Output $/M
$0.50
14
vs boards won of 57 shared

gpt-oss-20b or Llama 4 Scout: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick gpt-oss-20b for output tokens 3.3x cheaper ($0.15 vs $0.50 per million) and work measured by LMArena Text: hard prompts in English or LegalBench (Vals AI), where it leads.

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BLlama 4 ScoutMeta LlamaNot benchmarkedNo coding benchmark$1.276 per solved task
Shared results
57
gpt-oss-20b only
5
Llama 4 Scout only
25
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
gpt-oss-20b not benchmarked, Llama 4 Scout not benchmarked.
Widest category
Agentic work, 44.7 points apart on average over 1 shared benchmark.
Widest single gap
AIME 2025 (Artificial Analysis run): gpt-oss-20b 89.3% against Llama 4 Scout 14.0%, 75.3 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against Llama 4 Scout $0.50 per million output tokens, 3.3x apart.
Context window
gpt-oss-20b takes 131K 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
Categorygpt-oss-20bBarsLlama 4 ScoutTies
Coding60
Intelligence20
Agentic work10
Reasoning71
Math80
Knowledge73
Web design20
General1010
All shared boards4314
CodingLike-for-likeSix of these boards feed the Vibe Coding Index60
Coding benchmarks for gpt-oss-20b and Llama 4 Scout
Benchmarkgpt-oss-20bLlama 4 ScoutLeader
SWE-bench VerifiedNot measured9.1%Only Llama 4 Scout measured
AA Coding IndexNot measured8.2Only Llama 4 Scout measured
LiveCodeBench (Vals AI)80.4%38.5%gpt-oss-20b
LiveCodeBench (Artificial Analysis run)77.7%29.9%gpt-oss-20b
SciCode38.9%21.3%gpt-oss-20b
Terminal-Bench Hard (Artificial Analysis run)10.6%1.5%gpt-oss-20b
Terminal-Bench3.4%Not measuredOnly gpt-oss-20b measured
WeirdML40.9%Not measuredOnly gpt-oss-20b measured
ALE-Bench566.0Not measuredOnly gpt-oss-20b measured
LMArena Text: coding13071286gpt-oss-20b
LMArena Text: software and IT13111286gpt-oss-20b
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for gpt-oss-20b and Llama 4 Scout
Benchmarkgpt-oss-20bLlama 4 ScoutLeader
AA Intelligence Index10.06.5gpt-oss-20b
Epoch Capabilities Index137.7129.6gpt-oss-20b
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for gpt-oss-20b and Llama 4 Scout
Benchmarkgpt-oss-20bLlama 4 ScoutLeader
AA Agentic IndexNot measured0.5Only Llama 4 Scout measured
τ²-Bench Telecom60.2%15.5%gpt-oss-20b
Berkeley Function Calling Leaderboard (BFCL)Not measured28.1%Only Llama 4 Scout measured
BrowseComp-Plus50.6%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
Reasoning benchmarks for gpt-oss-20b and Llama 4 Scout
Benchmarkgpt-oss-20bLlama 4 ScoutLeader
GPQA Diamond68.9%47.0%gpt-oss-20b
MMMU Pro (Vals AI)Not measured58.8%Only Llama 4 Scout measured
GPQA Diamond (Artificial Analysis run)68.8%58.7%gpt-oss-20b
Humanity's Last Exam (Artificial Analysis run)11.0%3.8%gpt-oss-20b
GPQA Diamond (Epoch AI run)60.8%51.8%gpt-oss-20b
ARC-AGINot measured0.5%Only Llama 4 Scout measured
ARC-AGI-2Not measured0.0%Only Llama 4 Scout measured
LMArena Text: hard prompts12741266gpt-oss-20b
LMArena Text: expert12581235gpt-oss-20b
LMArena Text: hard prompts in English12921293Llama 4 Scout
LMArena Vision: diagramsNot measured1125Only Llama 4 Scout measured
LMArena Vision: homeworkNot measured1148Only Llama 4 Scout measured
Kagi LLM Benchmark53.2%36.9%gpt-oss-20b
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index80
Math benchmarks for gpt-oss-20b and Llama 4 Scout
Benchmarkgpt-oss-20bLlama 4 ScoutLeader
AIME86.0%19.0%gpt-oss-20b
MATH 500 (Vals AI)94.2%79.2%gpt-oss-20b
MGSM (Vals AI)89.0%88.0%gpt-oss-20b
AA Math Index89.314.0gpt-oss-20b
AIME 2025 (Artificial Analysis run)89.3%14.0%gpt-oss-20b
OTIS Mock AIME65.3%7.8%gpt-oss-20b
MATH level 5Not measured62.3%Only Llama 4 Scout measured
LMArena Text: math13171287gpt-oss-20b
LMArena Text: mathematical work13051286gpt-oss-20b
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index73
Knowledge benchmarks for gpt-oss-20b and Llama 4 Scout
Benchmarkgpt-oss-20bLlama 4 ScoutLeader
MMLU Pro71.6%69.6%gpt-oss-20b
LegalBench (Vals AI)70.8%72.0%Llama 4 Scout
CaseLaw (Vals AI)43.8%Not measuredOnly gpt-oss-20b measured
CorpFin (Vals AI)53.1%46.8%gpt-oss-20b
TaxEval (Vals AI)63.7%55.2%gpt-oss-20b
MortgageTax (Vals AI)Not measured57.8%Only Llama 4 Scout measured
MedQA (Vals AI)82.9%50.9%gpt-oss-20b
MedCode (Vals AI)Not measured23.3%Only Llama 4 Scout measured
MMLU Pro (Artificial Analysis run)74.8%75.2%Llama 4 Scout
LMArena Text: science12961278gpt-oss-20b
LMArena Text: medicine and healthcare13101275gpt-oss-20b
LMArena Text: legal and government12801285Llama 4 Scout
LMArena Text: business and finance12841257gpt-oss-20b
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index20
Web design benchmarks for gpt-oss-20b and Llama 4 Scout
Benchmarkgpt-oss-20bLlama 4 ScoutLeader
Design Arena: websites852750gpt-oss-20b
Design Arena: UI componentsNot measured768Only Llama 4 Scout measured
Design Arena: game devNot measured773Only Llama 4 Scout measured
Design Arena: data viz933896gpt-oss-20b
Design Arena: all code categoriesNot measured790Only Llama 4 Scout measured
Neither model has a result on the other 4 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index1010
General benchmarks for gpt-oss-20b and Llama 4 Scout
Benchmarkgpt-oss-20bLlama 4 ScoutLeader
SAGE (Vals AI)Not measured34.8%Only Llama 4 Scout measured
MedScribe (Vals AI)Not measured50.6%Only Llama 4 Scout measured
IFBench65.1%39.5%gpt-oss-20b
Long context reasoning (AA-LCR)34.7%27.7%gpt-oss-20b
DTBench68.0%57.9%gpt-oss-20b
LMCA14.5%12.0%gpt-oss-20b
Fiction.LiveBenchNot measured36.0%Only Llama 4 Scout measured
LMArena Text12881279gpt-oss-20b
LMArena Text: instruction following12361248Llama 4 Scout
LMArena Text: creative writing12011249Llama 4 Scout
LMArena VisionNot measured1118Only Llama 4 Scout measured
LMArena Text: English13031304Llama 4 Scout
LMArena Text: non-English12691252gpt-oss-20b
LMArena Text: Chinese13151255gpt-oss-20b
LMArena Text: German12551273Llama 4 Scout
LMArena Text: Japanese12441206gpt-oss-20b
LMArena Text: Korean12361207gpt-oss-20b
LMArena Text: FrenchNot measured1283Only Llama 4 Scout measured
LMArena Text: Spanish12671278Llama 4 Scout
LMArena Text: Russian12781263gpt-oss-20b
LMArena Text: Polish12521265Llama 4 Scout
LMArena Text: multi-turn12681280Llama 4 Scout
LMArena Text: longer queries12501265Llama 4 Scout
LMArena Text: writing and language12381269Llama 4 Scout
LMArena Text: entertainment and media12161242Llama 4 Scout
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 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for gpt-oss-20b and Llama 4 Scout
Benchmarkgpt-oss-20bLlama 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

gpt-oss-20b$0.0001Fits in one request
Llama 4 Scout$0.0004Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
Llama 4 Scout$0.010Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
Llama 4 Scout$0.040Fits in one request

gpt-oss-20b 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 gpt-oss-20b and Llama 4 Scout
SpecificationOpenAI gpt-oss-20bMeta Llama 4 Scout
MakerOpenAIMeta Llama
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025April 5, 2025
Context window131K1.31M
Input $/Mtok$0.03$0.175
Output $/Mtok$0.15$0.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computable$1.276
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-20b better than Llama 4 Scout for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 3.3x cheaper ($0.15 vs $0.50 per million) and work measured by LMArena Text: hard prompts in English or LegalBench (Vals AI), where it leads.

Which is cheaper, gpt-oss-20b or Llama 4 Scout?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Llama 4 Scout costs $0.175 and $0.50. Cost per solved task is known for Llama 4 Scout only.

Which has the bigger context window, gpt-oss-20b or Llama 4 Scout?

Llama 4 Scout, with 1.31M tokens against 131K.

How many benchmarks is the gpt-oss-20b vs Llama 4 Scout comparison based on?

57 benchmarks have a result for both models as of October 21, 2026. gpt-oss-20b's coding index rests on 0 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