Enter opens the highlighted result. Esc closes.

gpt-oss-120b vs Llama 4 Maverick

gpt-oss-120b leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 11.6 to 9.3, and gpt-oss-120b costs 2.0x less per output token ($0.50 vs $1.00 per million). Updated October 22, 2026; 69 benchmarks have a result for both.

Replace gpt-oss-120b Replace Llama 4 Maverick
gpt-oss-120bOpenAI
Coding
No data
Overall
50.0
Output $/M
$0.50
63
Llama 4 MaverickMeta Llama
Coding
No data
Overall
21.8
Output $/M
$1.00
6
vs boards won of 69 shared

gpt-oss-120b or Llama 4 Maverick: which to pick

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

Pick gpt-oss-120b for output tokens 2.0x cheaper ($0.50 vs $1.00 per million) and a lower cost per solved task ($0.51 against $1.491).

Model Agpt-oss-120bOpenAINot benchmarked1 independent benchmark$0.51 per solved taskModel BLlama 4 MaverickMeta LlamaNot benchmarkedNo coding benchmark$1.491 per solved task
Shared results
69
gpt-oss-120b only
16
Llama 4 Maverick only
16
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-120b not benchmarked, Llama 4 Maverick not benchmarked.
Widest category
Math, 36.5 points apart on average over 7 shared benchmarks.
Widest single gap
AIME 2025 (Artificial Analysis run): gpt-oss-120b 93.4% against Llama 4 Maverick 19.3%, 74.1 points apart on a 0 to 100 scale.
Output price
gpt-oss-120b $0.50 against Llama 4 Maverick $1.00 per million output tokens, 2.0x apart.
Context window
gpt-oss-120b takes 131K 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.

Boards won, where both have a result
Categorygpt-oss-120bBarsLlama 4 MaverickTies
Coding110
Intelligence20
Agentic work20
Reasoning71
Math61
Knowledge73
Web design60
General221
All shared boards636
CodingLike-for-likeSix of these boards feed the Vibe Coding Index110
Coding benchmarks for gpt-oss-120b and Llama 4 Maverick
Benchmarkgpt-oss-120bLlama 4 MaverickLeader
Aider polyglot41.8%15.6%gpt-oss-120b
SWE-bench Verified26.0%21.0%gpt-oss-120b
AA Coding Index30.416.3gpt-oss-120b
LiveCodeBench (Vals AI)83.2%47.3%gpt-oss-120b
SWE-bench Verified (Vals AI)33.6%Not measuredOnly gpt-oss-120b measured
LiveCodeBench (Artificial Analysis run)87.8%39.7%gpt-oss-120b
SciCode34.0%31.7%gpt-oss-120b
Terminal-Bench Hard (Artificial Analysis run)23.5%6.8%gpt-oss-120b
Terminal-Bench18.7%Not measuredOnly gpt-oss-120b measured
WeirdML48.2%24.5%gpt-oss-120b
ALE-Bench575.6173.0gpt-oss-120b
LMArena Text: coding13791301gpt-oss-120b
LMArena Text: software and IT13871299gpt-oss-120b
SciCode7.7%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 29 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for gpt-oss-120b and Llama 4 Maverick
Benchmarkgpt-oss-120bLlama 4 MaverickLeader
AA Intelligence Index11.69.3gpt-oss-120b
Epoch Capabilities Index139.8132.2gpt-oss-120b
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for gpt-oss-120b and Llama 4 Maverick
Benchmarkgpt-oss-120bLlama 4 MaverickLeader
AA Agentic Index3.70.6gpt-oss-120b
τ²-Bench Telecom65.8%17.8%gpt-oss-120b
APEX-Agents4.4%Not measuredOnly gpt-oss-120b measured
METR time horizons56.6%Not measuredOnly gpt-oss-120b measured
Vending-Bench 2-$22Not measuredOnly gpt-oss-120b measured
BrowseComp-Plus67.0%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
Reasoning benchmarks for gpt-oss-120b and Llama 4 Maverick
Benchmarkgpt-oss-120bLlama 4 MaverickLeader
GPQA Diamond78.5%69.4%gpt-oss-120b
MMMU Pro (Vals AI)Not measured71.7%Only Llama 4 Maverick measured
GPQA Diamond (Artificial Analysis run)78.2%67.1%gpt-oss-120b
Humanity's Last Exam (Artificial Analysis run)19.6%4.9%gpt-oss-120b
GPQA Diamond (Epoch AI run)75.8%Not measuredOnly gpt-oss-120b measured
ARC-AGINot measured4.4%Only Llama 4 Maverick measured
ARC-AGI-2Not measured0.0%Only Llama 4 Maverick measured
SimpleBench22.1%27.7%Llama 4 Maverick
Mystery game puzzles2.0%Not measuredOnly gpt-oss-120b measured
LMArena Text: hard prompts13641281gpt-oss-120b
LMArena Text: expert13561259gpt-oss-120b
LMArena Text: hard prompts in English13681295gpt-oss-120b
LMArena Vision: diagramsNot measured1134Only Llama 4 Maverick measured
LMArena Vision: homeworkNot measured1164Only Llama 4 Maverick measured
Kagi LLM Benchmark58.6%55.9%gpt-oss-120b
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index61
Math benchmarks for gpt-oss-120b and Llama 4 Maverick
Benchmarkgpt-oss-120bLlama 4 MaverickLeader
AIME92.6%25.2%gpt-oss-120b
MATH 500 (Vals AI)94.8%85.2%gpt-oss-120b
MGSM (Vals AI)92.0%92.4%Llama 4 Maverick
AA Math Index93.419.3gpt-oss-120b
AIME 2025 (Artificial Analysis run)93.4%19.3%gpt-oss-120b
OTIS Mock AIME88.9%Not measuredOnly gpt-oss-120b measured
LMArena Text: math13891299gpt-oss-120b
LMArena Text: mathematical work13861295gpt-oss-120b
MathArena15.1%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index73
Knowledge benchmarks for gpt-oss-120b and Llama 4 Maverick
Benchmarkgpt-oss-120bLlama 4 MaverickLeader
MMLU Pro79.2%79.4%Llama 4 Maverick
LegalBench (Vals AI)75.9%77.8%Llama 4 Maverick
CaseLaw (Vals AI)48.8%Not measuredOnly gpt-oss-120b measured
CorpFin (Vals AI)58.2%49.7%gpt-oss-120b
TaxEval (Vals AI)71.6%66.6%gpt-oss-120b
MortgageTax (Vals AI)Not measured58.5%Only Llama 4 Maverick measured
MedQA (Vals AI)91.4%43.3%gpt-oss-120b
MedCode (Vals AI)Not measured36.5%Only Llama 4 Maverick measured
MMLU Pro (Artificial Analysis run)80.8%80.9%Llama 4 Maverick
GeoBenchNot measured52.0%Only Llama 4 Maverick measured
LMArena Text: science13821288gpt-oss-120b
LMArena Text: medicine and healthcare13881275gpt-oss-120b
LMArena Text: legal and government13551286gpt-oss-120b
LMArena Text: business and finance13591260gpt-oss-120b
PRBench Finance43.8%Not measuredOnly gpt-oss-120b measured
PRBench Legal40.2%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for gpt-oss-120b and Llama 4 Maverick
Benchmarkgpt-oss-120bLlama 4 MaverickLeader
Design Arena: websites968871gpt-oss-120b
Design Arena: UI components924897gpt-oss-120b
Design Arena: game dev991837gpt-oss-120b
Design Arena: data viz987882gpt-oss-120b
Design Arena: 3D901900gpt-oss-120b
Design Arena: all code categories962879gpt-oss-120b
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index221
General benchmarks for gpt-oss-120b and Llama 4 Maverick
Benchmarkgpt-oss-120bLlama 4 MaverickLeader
SAGE (Vals AI)Not measured35.7%Only Llama 4 Maverick measured
MedScribe (Vals AI)Not measured54.2%Only Llama 4 Maverick measured
IFBench69.0%43.0%gpt-oss-120b
Long context reasoning (AA-LCR)52.0%50.0%gpt-oss-120b
DTBench76.3%61.9%gpt-oss-120b
LMCA22.1%15.9%gpt-oss-120b
Fiction.LiveBench44.4%46.2%Llama 4 Maverick
Creative writing (Lech Mazur)77.1%62.0%gpt-oss-120b
Surface Evolver Bench25.0%Not measuredOnly gpt-oss-120b measured
LMArena Text13661287gpt-oss-120b
LMArena Text: instruction following13181267gpt-oss-120b
LMArena Text: creative writing12741266gpt-oss-120b
LMArena VisionNot measured1142Only Llama 4 Maverick measured
LMArena Text: English13751303gpt-oss-120b
LMArena Text: non-English13511269gpt-oss-120b
LMArena Text: Chinese13851277gpt-oss-120b
LMArena Text: German13531291gpt-oss-120b
LMArena Text: Japanese13311206gpt-oss-120b
LMArena Text: Korean12821203gpt-oss-120b
LMArena Text: French13701259gpt-oss-120b
LMArena Text: Spanish13891293gpt-oss-120b
LMArena Text: Russian13431286gpt-oss-120b
LMArena Text: Polish13531275gpt-oss-120b
LMArena Text: multi-turn13401289gpt-oss-120b
LMArena Text: longer queries13191280gpt-oss-120b
LMArena Text: writing and language13061277gpt-oss-120b
LMArena Text: entertainment and media12921250gpt-oss-120b
LMArena Vision: EnglishNot measured1150Only Llama 4 Maverick measured
LMArena Vision: ChineseNot measured1141Only Llama 4 Maverick measured
LMArena Vision: reading textNot measured1143Only Llama 4 Maverick measured
LMArena Vision: humorNot measured1100Only Llama 4 Maverick measured
LMArena Vision: creative writingNot measured1099Only Llama 4 Maverick measured
MultiChallenge45.3%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for gpt-oss-120b and Llama 4 Maverick
Benchmarkgpt-oss-120bLlama 4 MaverickLeader
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-120b$0.0003Fits in one request
Llama 4 Maverick$0.0008Fits in one request

gpt-oss-120b costs less

Repository review

50K input + 3K output tokens

gpt-oss-120b$0.0065Fits in one request
Llama 4 Maverick$0.021Fits in one request

gpt-oss-120b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-120b$0.025Exceeds the context window
Llama 4 Maverick$0.080Fits in one request

gpt-oss-120b 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-120b and Llama 4 Maverick
SpecificationOpenAI gpt-oss-120bMeta Llama 4 Maverick
MakerOpenAIMeta Llama
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025April 5, 2025
Context window131K524K
Input $/Mtok$0.10$0.35
Output $/Mtok$0.50$1.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved task$0.51$1.491
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-120b better than Llama 4 Maverick for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-120b for output tokens 2.0x cheaper ($0.50 vs $1.00 per million) and a lower cost per solved task ($0.51 against $1.491).

Which is cheaper, gpt-oss-120b or Llama 4 Maverick?

gpt-oss-120b costs $0.10 per million input tokens and $0.50 per million output tokens; Llama 4 Maverick costs $0.35 and $1.00. Per solved SWE-bench Verified task, gpt-oss-120b costs $0.51 and Llama 4 Maverick $1.491.

Which has the bigger context window, gpt-oss-120b or Llama 4 Maverick?

Llama 4 Maverick, with 524K tokens against 131K.

How many benchmarks is the gpt-oss-120b vs Llama 4 Maverick comparison based on?

69 benchmarks have a result for both models as of October 22, 2026. gpt-oss-120b's coding index rests on 1 independent benchmark and Llama 4 Maverick's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next