Enter opens the highlighted result. Esc closes.

GPT-5.4 Nano vs gpt-oss-20b

GPT-5.4 Nano leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 20.7 to 10.0, and gpt-oss-20b costs 8.3x less per output token ($0.15 vs $1.25 per million). Updated October 22, 2026; 51 benchmarks have a result for both.

Replace GPT-5.4 Nano Replace gpt-oss-20b
GPT-5.4 NanoOpenAI
Coding
44.8
Overall
45.7
Output $/M
$1.25
50
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
1
vs boards won of 51 shared

GPT-5.4 Nano or gpt-oss-20b: which to pick

Only GPT-5.4 Nano has a coding score, 44.8 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding.

Pick gpt-oss-20b for output tokens 8.3x cheaper ($0.15 vs $1.25 per million) and work measured by Kagi LLM Benchmark, where it leads.

Model AGPT-5.4 NanoOpenAI44.8/1002 independent benchmarks$0.14 per solved taskModel Bgpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
51
GPT-5.4 Nano only
34
gpt-oss-20b only
11
Like-for-like categories
7 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-5.4 Nano 44.8 from 2 benchmarks, gpt-oss-20b not benchmarked.
Widest category
General, 17.7 points apart on average over 20 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): GPT-5.4 Nano 76.7% against gpt-oss-20b 34.7%, 42.0 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Nano $1.25 against gpt-oss-20b $0.15 per million output tokens, 8.3x apart.
Context window
GPT-5.4 Nano takes 400K tokens, gpt-oss-20b 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-5.4 NanoBarsgpt-oss-20bTies
Coding70
Intelligence20
Agentic work10
Reasoning71
Math40
Knowledge90
General200
All shared boards501
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for GPT-5.4 Nano and gpt-oss-20b
BenchmarkGPT-5.4 Nanogpt-oss-20bLeader
AA Coding Index56.1Not measuredOnly GPT-5.4 Nano measured
LiveCodeBench (Vals AI)84.0%80.4%GPT-5.4 Nano
SWE-bench Verified (Vals AI)69.8%Not measuredOnly GPT-5.4 Nano measured
Vibe Code Bench (Vals AI)26.1%Not measuredOnly GPT-5.4 Nano measured
Code migration (Vals AI)14.5%Not measuredOnly GPT-5.4 Nano measured
Terminal-Bench 2.1 (Vals AI)41.6%Not measuredOnly GPT-5.4 Nano measured
LiveCodeBench (Artificial Analysis run)Not measured77.7%Only gpt-oss-20b measured
SciCode47.2%38.9%GPT-5.4 Nano
Terminal-Bench Hard (Artificial Analysis run)42.4%10.6%GPT-5.4 Nano
Terminal-BenchNot measured3.4%Only gpt-oss-20b measured
WeirdML49.2%40.9%GPT-5.4 Nano
ALE-Bench1004.5566.0GPT-5.4 Nano
LMArena Text: coding14041307GPT-5.4 Nano
LMArena Text: software and IT14021311GPT-5.4 Nano
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.4 Nano and gpt-oss-20b
BenchmarkGPT-5.4 Nanogpt-oss-20bLeader
AA Intelligence Index20.710.0GPT-5.4 Nano
Epoch Capabilities Index146.0137.7GPT-5.4 Nano
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5.4 Nano and gpt-oss-20b
BenchmarkGPT-5.4 Nanogpt-oss-20bLeader
AA Agentic Index16.0Not measuredOnly GPT-5.4 Nano measured
Finance Agent (Vals AI)38.2%Not measuredOnly GPT-5.4 Nano measured
Tax Agent Bench (Vals AI)5.0%Not measuredOnly GPT-5.4 Nano measured
Legal Research Bench (Vals AI)6.3%Not measuredOnly GPT-5.4 Nano measured
Excel Modeling Benchmark (Vals AI)44.8%Not measuredOnly GPT-5.4 Nano measured
τ²-Bench Telecom76.0%60.2%GPT-5.4 Nano
BrowseComp-PlusNot measured50.6%Only gpt-oss-20b measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
Reasoning benchmarks for GPT-5.4 Nano and gpt-oss-20b
BenchmarkGPT-5.4 Nanogpt-oss-20bLeader
GPQA Diamond77.5%68.9%GPT-5.4 Nano
MMMU Pro (Vals AI)73.6%Not measuredOnly GPT-5.4 Nano measured
GPQA Diamond (Artificial Analysis run)81.7%68.8%GPT-5.4 Nano
Humanity's Last Exam (Artificial Analysis run)28.3%11.0%GPT-5.4 Nano
GPQA Diamond (Epoch AI run)78.5%60.8%GPT-5.4 Nano
ARC-AGI51.5%Not measuredOnly GPT-5.4 Nano measured
ARC-AGI-25.7%Not measuredOnly GPT-5.4 Nano measured
Chess puzzles45.0%Not measuredOnly GPT-5.4 Nano measured
Mystery game puzzles9.0%Not measuredOnly GPT-5.4 Nano measured
LMArena Text: hard prompts13811274GPT-5.4 Nano
LMArena Text: expert13961258GPT-5.4 Nano
LMArena Text: hard prompts in English13871292GPT-5.4 Nano
LMArena Vision: diagrams1210Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: homework1225Not measuredOnly GPT-5.4 Nano measured
Kagi LLM Benchmark39.7%53.2%gpt-oss-20b
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for GPT-5.4 Nano and gpt-oss-20b
BenchmarkGPT-5.4 Nanogpt-oss-20bLeader
AIME88.8%86.0%GPT-5.4 Nano
MATH 500 (Vals AI)Not measured94.2%Only gpt-oss-20b measured
MGSM (Vals AI)Not measured89.0%Only gpt-oss-20b measured
AA Math IndexNot measured89.3Only gpt-oss-20b measured
AIME 2025 (Artificial Analysis run)Not measured89.3%Only gpt-oss-20b measured
OTIS Mock AIME87.8%65.3%GPT-5.4 Nano
FrontierMath, tiers 1 to 344.9%Not measuredOnly GPT-5.4 Nano measured
FrontierMath, tier 412.2%Not measuredOnly GPT-5.4 Nano measured
ProofBench5.0%Not measuredOnly GPT-5.4 Nano measured
LMArena Text: math14051317GPT-5.4 Nano
LMArena Text: mathematical work14091305GPT-5.4 Nano
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index90
Knowledge benchmarks for GPT-5.4 Nano and gpt-oss-20b
BenchmarkGPT-5.4 Nanogpt-oss-20bLeader
MMLU Pro77.2%71.6%GPT-5.4 Nano
LegalBench (Vals AI)77.9%70.8%GPT-5.4 Nano
CaseLaw (Vals AI)51.9%43.8%GPT-5.4 Nano
CorpFin (Vals AI)61.2%53.1%GPT-5.4 Nano
TaxEval (Vals AI)67.4%63.7%GPT-5.4 Nano
MortgageTax (Vals AI)59.1%Not measuredOnly GPT-5.4 Nano measured
MedQA (Vals AI)Not measured82.9%Only gpt-oss-20b measured
MedCode (Vals AI)41.0%Not measuredOnly GPT-5.4 Nano measured
MMLU Pro (Artificial Analysis run)Not measured74.8%Only gpt-oss-20b measured
SimpleQA Verified11.7%Not measuredOnly GPT-5.4 Nano measured
LMArena Text: science13741296GPT-5.4 Nano
LMArena Text: medicine and healthcare13691310GPT-5.4 Nano
LMArena Text: legal and government13681280GPT-5.4 Nano
LMArena Text: business and finance13661284GPT-5.4 Nano
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Web design benchmarks for GPT-5.4 Nano and gpt-oss-20b
BenchmarkGPT-5.4 Nanogpt-oss-20bLeader
Design Arena: websitesNot measured852Only gpt-oss-20b measured
Design Arena: data vizNot measured933Only gpt-oss-20b measured
Neither model has a result on the other 7 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index200
General benchmarks for GPT-5.4 Nano and gpt-oss-20b
BenchmarkGPT-5.4 Nanogpt-oss-20bLeader
SAGE (Vals AI)38.1%Not measuredOnly GPT-5.4 Nano measured
MedScribe (Vals AI)77.1%Not measuredOnly GPT-5.4 Nano measured
Vals Multimodal Index47.6%Not measuredOnly GPT-5.4 Nano measured
IFBench75.9%65.1%GPT-5.4 Nano
Long context reasoning (AA-LCR)76.7%34.7%GPT-5.4 Nano
DTBench80.3%68.0%GPT-5.4 Nano
LMCA36.9%14.5%GPT-5.4 Nano
LMArena Text13721288GPT-5.4 Nano
LMArena Text: instruction following13621236GPT-5.4 Nano
LMArena Text: creative writing13151201GPT-5.4 Nano
LMArena Vision1196Not measuredOnly GPT-5.4 Nano measured
LMArena Text: English13811303GPT-5.4 Nano
LMArena Text: non-English13591269GPT-5.4 Nano
LMArena Text: Chinese13911315GPT-5.4 Nano
LMArena Text: German13681255GPT-5.4 Nano
LMArena Text: Japanese13431244GPT-5.4 Nano
LMArena Text: Korean13211236GPT-5.4 Nano
LMArena Text: French1395Not measuredOnly GPT-5.4 Nano measured
LMArena Text: Spanish13711267GPT-5.4 Nano
LMArena Text: Russian13631278GPT-5.4 Nano
LMArena Text: Polish13661252GPT-5.4 Nano
LMArena Text: multi-turn13821268GPT-5.4 Nano
LMArena Text: longer queries13651250GPT-5.4 Nano
LMArena Text: writing and language13381238GPT-5.4 Nano
LMArena Text: entertainment and media13251216GPT-5.4 Nano
LMArena Vision: English1202Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: Chinese1232Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: reading text1204Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: humor1161Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: recognizing things1141Not measuredOnly GPT-5.4 Nano measured
LMArena Vision: creative writing1159Not measuredOnly GPT-5.4 Nano 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-5.4 Nano and gpt-oss-20b
BenchmarkGPT-5.4 Nanogpt-oss-20bLeader
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-5.4 Nano$0.0008Fits in one request
gpt-oss-20b$0.0001Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Nano$0.014Fits in one request
gpt-oss-20b$0.0019Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Nano$0.052Fits in one request
gpt-oss-20b$0.0075Exceeds the context window

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-5.4 Nano and gpt-oss-20b
SpecificationOpenAI GPT-5.4 NanoOpenAI gpt-oss-20b
MakerOpenAIOpenAI
WeightsNo public weights listedOpen weights
ReleasedMarch 17, 2026August 5, 2025
Context window400K131K
Input $/Mtok$0.20$0.03
Output $/Mtok$1.25$0.15
Coding index44.8Not benchmarked
Independent measurements behind it20
Cost per solved task$0.14Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Nano better than gpt-oss-20b for coding?

Only GPT-5.4 Nano has a coding score, 44.8 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 8.3x cheaper ($0.15 vs $1.25 per million) and work measured by Kagi LLM Benchmark, where it leads.

Which is cheaper, GPT-5.4 Nano or gpt-oss-20b?

GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for GPT-5.4 Nano only.

Which has the bigger context window, GPT-5.4 Nano or gpt-oss-20b?

GPT-5.4 Nano, with 400K tokens against 131K.

How many benchmarks is the GPT-5.4 Nano vs gpt-oss-20b comparison based on?

51 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Nano's coding index rests on 2 independent benchmarks and gpt-oss-20b's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next