Enter opens the highlighted result. Esc closes.

GPT-5 Mini vs gpt-oss-120b

GPT-5 Mini leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 20.6 to 11.6, and gpt-oss-120b costs 4.0x less per output token ($0.50 vs $2.00 per million). Updated October 21, 2026; 71 benchmarks have a result for both.

Replace GPT-5 Mini Replace gpt-oss-120b
GPT-5 MiniOpenAI
Coding
34.2
Overall
43.7
Output $/M
$2.00
57
gpt-oss-120bOpenAI
Coding
No data
Overall
50.0
Output $/M
$0.50
13
vs boards won of 71 shared, 1 tied

GPT-5 Mini or gpt-oss-120b: which to pick

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding.

Pick gpt-oss-120b for output tokens 4.0x cheaper ($0.50 vs $2.00 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Vending-Bench 2, where it leads.

Model AGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved taskModel Bgpt-oss-120bOpenAINot benchmarked1 independent benchmark$0.51 per solved task
Shared results
71
GPT-5 Mini only
30
gpt-oss-120b only
10
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-5 Mini 34.2 from 2 benchmarks, gpt-oss-120b not benchmarked.
Widest category
Web design, 18.9 points apart on average over 6 shared benchmarks.
Widest single gap
SWE-bench Verified: GPT-5 Mini 59.8% against gpt-oss-120b 26.0%, 33.8 points apart on a 0 to 100 scale.
Output price
GPT-5 Mini $2.00 against gpt-oss-120b $0.50 per million output tokens, 4.0x apart.
Context window
GPT-5 Mini takes 400K tokens, gpt-oss-120b 131K.

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-5 MiniBarsgpt-oss-120bTies
Coding91
Intelligence20
Agentic work11
Reasoning81
Math161 tie
Knowledge83
Web design60
General221
All shared boards57131 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index91
Coding benchmarks for GPT-5 Mini and gpt-oss-120b
BenchmarkGPT-5 Minigpt-oss-120bLeader
Aider polyglotNot measured41.8%Only gpt-oss-120b measured
SWE-bench Verified59.8%26.0%GPT-5 Mini
SWE-bench Multilingual39.7%Not measuredOnly GPT-5 Mini measured
AA Coding IndexNot measured30.4Only gpt-oss-120b measured
LiveCodeBench (Vals AI)86.6%83.2%GPT-5 Mini
SWE-bench Verified (Vals AI)60.8%33.6%GPT-5 Mini
Vibe Code Bench (Vals AI)14.2%Not measuredOnly GPT-5 Mini measured
LiveCodeBench (Artificial Analysis run)83.8%87.8%gpt-oss-120b
SciCode39.0%34.0%GPT-5 Mini
Terminal-Bench Hard (Artificial Analysis run)33.3%23.5%GPT-5 Mini
Terminal-Bench34.8%18.7%GPT-5 Mini
WeirdML52.7%48.2%GPT-5 Mini
ALE-BenchNot measured575.6Only gpt-oss-120b measured
LMArena Text: coding14061379GPT-5 Mini
LMArena Text: software and IT13941387GPT-5 Mini
SciCodeNot measured7.7%Only gpt-oss-120b measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5 Mini and gpt-oss-120b
BenchmarkGPT-5 Minigpt-oss-120bLeader
AA Intelligence Index20.611.6GPT-5 Mini
Epoch Capabilities Index145.3139.8GPT-5 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for GPT-5 Mini and gpt-oss-120b
BenchmarkGPT-5 Minigpt-oss-120bLeader
AA Agentic IndexNot measured3.7Only gpt-oss-120b measured
τ²-Bench Telecom71.1%65.8%GPT-5 Mini
APEX-AgentsNot measured4.4%Only gpt-oss-120b measured
METR time horizonsNot measured56.6%Only gpt-oss-120b measured
Vending-Bench 2-$31-$22gpt-oss-120b
Berkeley Function Calling Leaderboard (BFCL)55.5%Not measuredOnly GPT-5 Mini measured
BrowseComp-PlusNot measured67.0%Only 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 index81
Reasoning benchmarks for GPT-5 Mini and gpt-oss-120b
BenchmarkGPT-5 Minigpt-oss-120bLeader
GPQA Diamond80.3%78.5%GPT-5 Mini
MMMU Pro (Vals AI)78.9%Not measuredOnly GPT-5 Mini measured
GPQA Diamond (Artificial Analysis run)82.8%78.2%GPT-5 Mini
Humanity's Last Exam (Artificial Analysis run)21.5%19.6%GPT-5 Mini
GPQA Diamond (Epoch AI run)75.0%75.8%gpt-oss-120b
ARC-AGI54.3%Not measuredOnly GPT-5 Mini measured
ARC-AGI-24.4%Not measuredOnly GPT-5 Mini measured
SimpleBenchNot measured22.1%Only gpt-oss-120b measured
Chess puzzles24.0%Not measuredOnly GPT-5 Mini measured
Mystery game puzzles10.0%2.0%GPT-5 Mini
VPCT40.2%Not measuredOnly GPT-5 Mini measured
LMArena Text: hard prompts13801364GPT-5 Mini
LMArena Text: expert13791356GPT-5 Mini
LMArena Text: hard prompts in English13831368GPT-5 Mini
LMArena Vision: diagrams1202Not measuredOnly GPT-5 Mini measured
LMArena Vision: homework1210Not measuredOnly GPT-5 Mini measured
Kagi LLM Benchmark70.3%58.6%GPT-5 Mini
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index16
Math benchmarks for GPT-5 Mini and gpt-oss-120b
BenchmarkGPT-5 Minigpt-oss-120bLeader
AIME91.5%92.6%gpt-oss-120b
MATH 500 (Vals AI)94.8%94.8%Tie
MGSM (Vals AI)92.6%92.0%GPT-5 Mini
AA Math Index90.793.4gpt-oss-120b
AIME 2025 (Artificial Analysis run)90.7%93.4%gpt-oss-120b
OTIS Mock AIME86.7%88.9%gpt-oss-120b
FrontierMath, tiers 1 to 346.7%Not measuredOnly GPT-5 Mini measured
FrontierMath, tier 412.2%Not measuredOnly GPT-5 Mini measured
ProofBench9.0%Not measuredOnly GPT-5 Mini measured
MATH level 597.8%Not measuredOnly GPT-5 Mini measured
LMArena Text: math13781389gpt-oss-120b
LMArena Text: mathematical work13801386gpt-oss-120b
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index83
Knowledge benchmarks for GPT-5 Mini and gpt-oss-120b
BenchmarkGPT-5 Minigpt-oss-120bLeader
MMLU Pro82.2%79.2%GPT-5 Mini
LegalBench (Vals AI)81.8%75.9%GPT-5 Mini
CaseLaw (Vals AI)68.5%48.8%GPT-5 Mini
CorpFin (Vals AI)60.2%58.2%GPT-5 Mini
TaxEval (Vals AI)75.2%71.6%GPT-5 Mini
MortgageTax (Vals AI)66.9%Not measuredOnly GPT-5 Mini measured
MedQA (Vals AI)96.1%91.4%GPT-5 Mini
MedCode (Vals AI)43.0%Not measuredOnly GPT-5 Mini measured
MMLU Pro (Artificial Analysis run)83.7%80.8%GPT-5 Mini
SimpleQA Verified21.6%Not measuredOnly GPT-5 Mini measured
LMArena Text: science13711382gpt-oss-120b
LMArena Text: medicine and healthcare13801388gpt-oss-120b
LMArena Text: legal and government13751355GPT-5 Mini
LMArena Text: business and finance13581359gpt-oss-120b
FACTS Benchmark Suite38.6%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for GPT-5 Mini and gpt-oss-120b
BenchmarkGPT-5 Minigpt-oss-120bLeader
Design Arena: websites1125968GPT-5 Mini
Design Arena: UI components1106927GPT-5 Mini
Design Arena: game dev1130992GPT-5 Mini
Design Arena: data viz1130987GPT-5 Mini
Design Arena: 3D1037901GPT-5 Mini
Design Arena: all code categories1115963GPT-5 Mini
Design Arena: SVG1091Not measuredOnly GPT-5 Mini measured
Design Arena: ASCII art1125Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index221
General benchmarks for GPT-5 Mini and gpt-oss-120b
BenchmarkGPT-5 Minigpt-oss-120bLeader
SAGE (Vals AI)43.0%Not measuredOnly GPT-5 Mini measured
MedScribe (Vals AI)80.6%Not measuredOnly GPT-5 Mini measured
IFBench75.4%69.0%GPT-5 Mini
Long context reasoning (AA-LCR)72.3%52.0%GPT-5 Mini
DTBench80.5%76.3%GPT-5 Mini
LMCA34.2%22.1%GPT-5 Mini
Fiction.LiveBench69.4%44.4%GPT-5 Mini
Creative writing (Lech Mazur)83.1%77.1%GPT-5 Mini
Surface Evolver BenchNot measured25.0%Only gpt-oss-120b measured
LMArena Text13731366GPT-5 Mini
LMArena Text: instruction following13571318GPT-5 Mini
LMArena Text: creative writing13251274GPT-5 Mini
LMArena Vision1202Not measuredOnly GPT-5 Mini measured
LMArena Text: English13791375GPT-5 Mini
LMArena Text: non-English13631351GPT-5 Mini
LMArena Text: Chinese13861385GPT-5 Mini
LMArena Text: German13661353GPT-5 Mini
LMArena Text: Japanese13411331GPT-5 Mini
LMArena Text: Korean13081282GPT-5 Mini
LMArena Text: French13861370GPT-5 Mini
LMArena Text: Spanish13541389gpt-oss-120b
LMArena Text: Russian13621343GPT-5 Mini
LMArena Text: Polish13781353GPT-5 Mini
LMArena Text: multi-turn13631340GPT-5 Mini
LMArena Text: longer queries13551319GPT-5 Mini
LMArena Text: writing and language13441306GPT-5 Mini
LMArena Text: entertainment and media13401292GPT-5 Mini
LMArena Vision: English1216Not measuredOnly GPT-5 Mini measured
LMArena Vision: Chinese1214Not measuredOnly GPT-5 Mini measured
LMArena Vision: reading text1199Not measuredOnly GPT-5 Mini measured
LMArena Vision: humor1205Not measuredOnly GPT-5 Mini measured
LMArena Vision: captioning1217Not measuredOnly GPT-5 Mini measured
LMArena Vision: recognizing things1226Not measuredOnly GPT-5 Mini measured
LMArena Vision: creative writing1181Not measuredOnly GPT-5 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-5 Mini and gpt-oss-120b
BenchmarkGPT-5 Minigpt-oss-120bLeader
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-5 Mini$0.0013Fits in one request
gpt-oss-120b$0.0003Fits in one request

gpt-oss-120b costs less

Repository review

50K input + 3K output tokens

GPT-5 Mini$0.018Fits in one request
gpt-oss-120b$0.0065Fits in one request

gpt-oss-120b costs less

Agent loop

200K input + 10K output tokens

GPT-5 Mini$0.070Fits in one request
gpt-oss-120b$0.025Exceeds 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-5 Mini and gpt-oss-120b
SpecificationOpenAI GPT-5 MiniOpenAI gpt-oss-120b
MakerOpenAIOpenAI
WeightsNo public weights listedOpen weights
ReleasedAugust 7, 2025August 5, 2025
Context window400K131K
Input $/Mtok$0.25$0.10
Output $/Mtok$2.00$0.50
Coding index34.2Not benchmarked
Independent measurements behind it21
Cost per solved task$0.08$0.51
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 Mini better than gpt-oss-120b for coding?

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding. Pick gpt-oss-120b for output tokens 4.0x cheaper ($0.50 vs $2.00 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Vending-Bench 2, where it leads.

Which is cheaper, GPT-5 Mini or gpt-oss-120b?

GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens; gpt-oss-120b costs $0.10 and $0.50. Per solved SWE-bench Verified task, GPT-5 Mini costs $0.08 and gpt-oss-120b $0.51.

Which has the bigger context window, GPT-5 Mini or gpt-oss-120b?

GPT-5 Mini, with 400K tokens against 131K.

How many benchmarks is the GPT-5 Mini vs gpt-oss-120b comparison based on?

71 benchmarks have a result for both models as of October 21, 2026. GPT-5 Mini's coding index rests on 2 independent benchmarks and gpt-oss-120b's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next