Enter opens the highlighted result. Esc closes.

gpt-oss-120b vs o4 Mini

o4 Mini leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 16.7 to 11.6, and gpt-oss-120b costs 8.8x less per output token ($0.50 vs $4.40 per million). Updated October 22, 2026; 70 benchmarks have a result for both.

Replace gpt-oss-120b Replace o4 Mini
gpt-oss-120bOpenAI
Coding
No data
Overall
50.0
Output $/M
$0.50
34
o4 MiniOpenAI
Coding
No data
Overall
43.0
Output $/M
$4.40
36
vs boards won of 70 shared

gpt-oss-120b or o4 Mini: 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 8.8x cheaper ($0.50 vs $4.40 per million) and work measured by Aider polyglot or SWE-bench Verified, where it leads.

Model Agpt-oss-120bOpenAINot benchmarked1 independent benchmark$0.51 per solved taskModel Bo4 MiniOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
70
gpt-oss-120b only
11
o4 Mini only
28
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, o4 Mini not benchmarked.
Widest category
Coding, 10.3 points apart on average over 9 shared benchmarks.
Widest single gap
SWE-bench Verified: gpt-oss-120b 26.0% against o4 Mini 64.6%, 38.6 points apart on a 0 to 100 scale.
Output price
gpt-oss-120b $0.50 against o4 Mini $4.40 per million output tokens, 8.8x apart.
Context window
gpt-oss-120b takes 131K tokens, o4 Mini 200K.

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-120bBarso4 MiniTies
Coding54
Intelligence02
Agentic work11
Reasoning55
Math62
Knowledge46
Web design15
General1211
All shared boards3436
CodingLike-for-likeSix of these boards feed the Vibe Coding Index54
Coding benchmarks for gpt-oss-120b and o4 Mini
Benchmarkgpt-oss-120bo4 MiniLeader
Aider polyglot41.8%72.0%o4 Mini
SWE-bench Verified26.0%64.6%o4 Mini
SWE-bench MultimodalNot measured33.9%Only o4 Mini measured
AA Coding Index30.4Not measuredOnly gpt-oss-120b measured
LiveCodeBench (Vals AI)83.2%82.2%gpt-oss-120b
SWE-bench Verified (Vals AI)33.6%Not measuredOnly gpt-oss-120b measured
LiveCodeBench (Artificial Analysis run)87.8%85.9%gpt-oss-120b
SciCode34.0%Not measuredOnly gpt-oss-120b measured
Terminal-Bench Hard (Artificial Analysis run)23.5%15.2%gpt-oss-120b
Terminal-Bench18.7%Not measuredOnly gpt-oss-120b measured
GSO-BenchNot measured3.6%Only o4 Mini measured
WeirdML48.2%52.6%o4 Mini
ALE-Bench575.6Not measuredOnly gpt-oss-120b measured
LMArena Text: coding13791368gpt-oss-120b
LMArena Text: software and IT13871367gpt-oss-120b
SciCode7.7%10.8%o4 Mini
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for gpt-oss-120b and o4 Mini
Benchmarkgpt-oss-120bo4 MiniLeader
AA Intelligence Index11.616.7o4 Mini
Epoch Capabilities Index139.8145.5o4 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for gpt-oss-120b and o4 Mini
Benchmarkgpt-oss-120bo4 MiniLeader
AA Agentic Index3.7Not measuredOnly gpt-oss-120b measured
τ²-Bench Telecom65.8%55.6%gpt-oss-120b
APEX-Agents4.4%Not measuredOnly gpt-oss-120b measured
METR time horizons56.6%63.9%o4 Mini
Vending-Bench 2-$22Not measuredOnly gpt-oss-120b measured
Berkeley Function Calling Leaderboard (BFCL)Not measured53.2%Only o4 Mini measured
BrowseComp-Plus67.0%Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index55
Reasoning benchmarks for gpt-oss-120b and o4 Mini
Benchmarkgpt-oss-120bo4 MiniLeader
GPQA Diamond78.5%74.5%gpt-oss-120b
MMMU Pro (Vals AI)Not measured79.7%Only o4 Mini measured
GPQA Diamond (Artificial Analysis run)78.2%78.4%o4 Mini
Humanity's Last Exam (Artificial Analysis run)19.6%16.5%gpt-oss-120b
GPQA Diamond (Epoch AI run)75.8%79.6%o4 Mini
ARC-AGINot measured58.7%Only o4 Mini measured
ARC-AGI-2Not measured6.1%Only o4 Mini measured
SimpleBench22.1%38.7%o4 Mini
Chess puzzlesNot measured22.0%Only o4 Mini measured
Mystery game puzzles2.0%5.0%o4 Mini
VPCTNot measured57.5%Only o4 Mini measured
LMArena Text: hard prompts13641351gpt-oss-120b
LMArena Text: expert13561343gpt-oss-120b
LMArena Text: hard prompts in English13681366gpt-oss-120b
LMArena Vision: diagramsNot measured1197Only o4 Mini measured
LMArena Vision: homeworkNot measured1234Only o4 Mini measured
Kagi LLM Benchmark58.6%67.6%o4 Mini
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index62
Math benchmarks for gpt-oss-120b and o4 Mini
Benchmarkgpt-oss-120bo4 MiniLeader
AIME92.6%83.7%gpt-oss-120b
MATH 500 (Vals AI)94.8%94.2%gpt-oss-120b
MGSM (Vals AI)92.0%93.4%o4 Mini
AA Math Index93.490.7gpt-oss-120b
AIME 2025 (Artificial Analysis run)93.4%90.7%gpt-oss-120b
OTIS Mock AIME88.9%81.7%gpt-oss-120b
FrontierMath, tiers 1 to 3Not measured36.1%Only o4 Mini measured
FrontierMath, tier 4Not measured4.9%Only o4 Mini measured
MATH level 5Not measured97.8%Only o4 Mini measured
LMArena Text: math13891389o4 Mini
LMArena Text: mathematical work13861379gpt-oss-120b
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index46
Knowledge benchmarks for gpt-oss-120b and o4 Mini
Benchmarkgpt-oss-120bo4 MiniLeader
MMLU Pro79.2%80.6%o4 Mini
LegalBench (Vals AI)75.9%79.2%o4 Mini
CaseLaw (Vals AI)48.8%Not measuredOnly gpt-oss-120b measured
CorpFin (Vals AI)58.2%59.0%o4 Mini
TaxEval (Vals AI)71.6%74.8%o4 Mini
MortgageTax (Vals AI)Not measured64.8%Only o4 Mini measured
MedQA (Vals AI)91.4%96.0%o4 Mini
MedCode (Vals AI)Not measured33.8%Only o4 Mini measured
MMLU Pro (Artificial Analysis run)80.8%83.2%o4 Mini
SimpleQA VerifiedNot measured19.6%Only o4 Mini measured
GeoBenchNot measured64.0%Only o4 Mini measured
LMArena Text: science13821354gpt-oss-120b
LMArena Text: medicine and healthcare13881361gpt-oss-120b
LMArena Text: legal and government13551350gpt-oss-120b
LMArena Text: business and finance13591325gpt-oss-120b
FACTS Benchmark SuiteNot measured28.1%Only o4 Mini measured
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index15
Web design benchmarks for gpt-oss-120b and o4 Mini
Benchmarkgpt-oss-120bo4 MiniLeader
Design Arena: websites967985o4 Mini
Design Arena: UI components924983o4 Mini
Design Arena: game dev9921003o4 Mini
Design Arena: data viz987991o4 Mini
Design Arena: 3D901854gpt-oss-120b
Design Arena: all code categories962976o4 Mini
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index1211
General benchmarks for gpt-oss-120b and o4 Mini
Benchmarkgpt-oss-120bo4 MiniLeader
SAGE (Vals AI)Not measured41.1%Only o4 Mini measured
MedScribe (Vals AI)Not measured69.1%Only o4 Mini measured
IFBench69.0%68.7%gpt-oss-120b
Long context reasoning (AA-LCR)52.0%61.0%o4 Mini
DTBench76.3%77.6%o4 Mini
LMCA22.1%26.5%o4 Mini
Fiction.LiveBench44.4%77.8%o4 Mini
Creative writing (Lech Mazur)77.1%75.0%gpt-oss-120b
Surface Evolver Bench25.0%Not measuredOnly gpt-oss-120b measured
LMArena Text13661353gpt-oss-120b
LMArena Text: instruction following13181320o4 Mini
LMArena Text: creative writing12741294o4 Mini
LMArena VisionNot measured1194Only o4 Mini measured
LMArena Text: English13751367gpt-oss-120b
LMArena Text: non-English13511337gpt-oss-120b
LMArena Text: Chinese13851354gpt-oss-120b
LMArena Text: German13531336gpt-oss-120b
LMArena Text: Japanese13311308gpt-oss-120b
LMArena Text: Korean12821312o4 Mini
LMArena Text: French13701364gpt-oss-120b
LMArena Text: Spanish13891346gpt-oss-120b
LMArena Text: Russian13431334gpt-oss-120b
LMArena Text: Polish13531358o4 Mini
LMArena Text: multi-turn13401350o4 Mini
LMArena Text: longer queries13191315gpt-oss-120b
LMArena Text: writing and language13061316o4 Mini
LMArena Text: entertainment and media12921308o4 Mini
LMArena Vision: EnglishNot measured1200Only o4 Mini measured
LMArena Vision: ChineseNot measured1218Only o4 Mini measured
LMArena Vision: reading textNot measured1197Only o4 Mini measured
LMArena Vision: humorNot measured1199Only o4 Mini measured
LMArena Vision: captioningNot measured1204Only o4 Mini measured
LMArena Vision: recognizing thingsNot measured1218Only o4 Mini measured
LMArena Vision: creative writingNot measured1166Only o4 Mini measured
Neither model has a result on the other 12 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 o4 Mini
Benchmarkgpt-oss-120bo4 MiniLeader
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
o4 Mini$0.0033Fits in one request

gpt-oss-120b costs less

Repository review

50K input + 3K output tokens

gpt-oss-120b$0.0065Fits in one request
o4 Mini$0.068Fits in one request

gpt-oss-120b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-120b$0.025Exceeds the context window
o4 Mini$0.264Exceeds the context window

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 o4 Mini
SpecificationOpenAI gpt-oss-120bOpenAI o4 Mini
MakerOpenAIOpenAI
WeightsOpen weightsNo public weights listed
ReleasedAugust 5, 2025April 16, 2025
Context window131K200K
Input $/Mtok$0.10$1.10
Output $/Mtok$0.50$4.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved task$0.51Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-120b better than o4 Mini for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick gpt-oss-120b for output tokens 8.8x cheaper ($0.50 vs $4.40 per million) and work measured by Aider polyglot or SWE-bench Verified, where it leads.

Which is cheaper, gpt-oss-120b or o4 Mini?

gpt-oss-120b costs $0.10 per million input tokens and $0.50 per million output tokens; o4 Mini costs $1.10 and $4.40. Cost per solved task is known for gpt-oss-120b only.

Which has the bigger context window, gpt-oss-120b or o4 Mini?

o4 Mini, with 200K tokens against 131K.

How many benchmarks is the gpt-oss-120b vs o4 Mini comparison based on?

70 benchmarks have a result for both models as of October 22, 2026. gpt-oss-120b's coding index rests on 1 independent benchmark and o4 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next