Enter opens the highlighted result. Esc closes.

GPT-5 Nano vs gpt-oss-20b

GPT-5 Nano leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 13.0 to 10.0, and gpt-oss-20b costs 2.7x less per output token ($0.15 vs $0.40 per million). Updated October 22, 2026; 58 benchmarks have a result for both.

Replace GPT-5 Nano Replace gpt-oss-20b
GPT-5 NanoOpenAI
Coding
No data
Overall
35.6
Output $/M
$0.40
44
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
14
vs boards won of 58 shared

GPT-5 Nano or gpt-oss-20b: which to pick

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

Pick GPT-5 Nano for a larger context window (400K against 131K tokens) and work measured by LiveCodeBench (Vals AI) or WeirdML, where it leads.

Model AGPT-5 NanoOpenAINot benchmarkedNo coding benchmark$0.109 per solved taskModel Bgpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
58
GPT-5 Nano only
29
gpt-oss-20b only
4
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 Nano not benchmarked, gpt-oss-20b not benchmarked.
Widest category
Agentic work, 23.7 points apart on average over 1 shared benchmark.
Widest single gap
Design Arena: websites: GPT-5 Nano 1101 against gpt-oss-20b 852, 31.1 points apart on a 0 to 100 scale.
Output price
GPT-5 Nano $0.40 against gpt-oss-20b $0.15 per million output tokens, 2.7x apart.
Context window
GPT-5 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 NanoBarsgpt-oss-20bTies
Coding52
Intelligence20
Agentic work01
Reasoning53
Math44
Knowledge91
Web design20
General173
All shared boards4414
CodingLike-for-likeSix of these boards feed the Vibe Coding Index52
Coding benchmarks for GPT-5 Nano and gpt-oss-20b
BenchmarkGPT-5 Nanogpt-oss-20bLeader
SWE-bench Verified34.8%Not measuredOnly GPT-5 Nano measured
LiveCodeBench (Vals AI)70.2%80.4%gpt-oss-20b
LiveCodeBench (Artificial Analysis run)78.9%77.7%GPT-5 Nano
SciCodeNot measured38.9%Only gpt-oss-20b measured
Terminal-Bench Hard (Artificial Analysis run)17.4%10.6%GPT-5 Nano
Terminal-Bench21.8%3.4%GPT-5 Nano
WeirdML38.1%40.9%gpt-oss-20b
ALE-BenchNot measured566.0Only gpt-oss-20b measured
LMArena Text: coding13511307GPT-5 Nano
LMArena Text: software and IT13451311GPT-5 Nano
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-5 Nano and gpt-oss-20b
BenchmarkGPT-5 Nanogpt-oss-20bLeader
AA Intelligence Index13.010.0GPT-5 Nano
Epoch Capabilities Index139.2137.7GPT-5 Nano
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-5 Nano and gpt-oss-20b
BenchmarkGPT-5 Nanogpt-oss-20bLeader
τ²-Bench Telecom36.5%60.2%gpt-oss-20b
Berkeley Function Calling Leaderboard (BFCL)51.4%Not measuredOnly GPT-5 Nano measured
BrowseComp-PlusNot measured50.6%Only gpt-oss-20b measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index53
Reasoning benchmarks for GPT-5 Nano and gpt-oss-20b
BenchmarkGPT-5 Nanogpt-oss-20bLeader
GPQA Diamond63.4%68.9%gpt-oss-20b
MMMU Pro (Vals AI)70.9%Not measuredOnly GPT-5 Nano measured
GPQA Diamond (Artificial Analysis run)67.6%68.8%gpt-oss-20b
Humanity's Last Exam (Artificial Analysis run)9.5%11.0%gpt-oss-20b
GPQA Diamond (Epoch AI run)69.4%60.8%GPT-5 Nano
ARC-AGI20.7%Not measuredOnly GPT-5 Nano measured
ARC-AGI-22.6%Not measuredOnly GPT-5 Nano measured
Chess puzzles22.0%Not measuredOnly GPT-5 Nano measured
Mystery game puzzles9.0%Not measuredOnly GPT-5 Nano measured
VPCT37.2%Not measuredOnly GPT-5 Nano measured
LMArena Text: hard prompts13281274GPT-5 Nano
LMArena Text: expert13211258GPT-5 Nano
LMArena Text: hard prompts in English13381292GPT-5 Nano
LMArena Vision: diagrams1141Not measuredOnly GPT-5 Nano measured
LMArena Vision: homework1157Not measuredOnly GPT-5 Nano measured
Kagi LLM Benchmark62.2%53.2%GPT-5 Nano
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index44
Math benchmarks for GPT-5 Nano and gpt-oss-20b
BenchmarkGPT-5 Nanogpt-oss-20bLeader
AIME81.2%86.0%gpt-oss-20b
MATH 500 (Vals AI)93.8%94.2%gpt-oss-20b
MGSM (Vals AI)89.3%89.0%GPT-5 Nano
AA Math Index83.789.3gpt-oss-20b
AIME 2025 (Artificial Analysis run)83.7%89.3%gpt-oss-20b
OTIS Mock AIME81.1%65.3%GPT-5 Nano
FrontierMath, tiers 1 to 320.0%Not measuredOnly GPT-5 Nano measured
FrontierMath, tier 42.4%Not measuredOnly GPT-5 Nano measured
ProofBench12.0%Not measuredOnly GPT-5 Nano measured
MATH level 595.2%Not measuredOnly GPT-5 Nano measured
LMArena Text: math13171317GPT-5 Nano
LMArena Text: mathematical work13261305GPT-5 Nano
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index91
Knowledge benchmarks for GPT-5 Nano and gpt-oss-20b
BenchmarkGPT-5 Nanogpt-oss-20bLeader
MMLU Pro76.1%71.6%GPT-5 Nano
LegalBench (Vals AI)50.1%70.8%gpt-oss-20b
CaseLaw (Vals AI)52.6%43.8%GPT-5 Nano
CorpFin (Vals AI)Not measured53.1%Only gpt-oss-20b measured
TaxEval (Vals AI)67.4%63.7%GPT-5 Nano
MortgageTax (Vals AI)53.6%Not measuredOnly GPT-5 Nano measured
MedQA (Vals AI)93.3%82.9%GPT-5 Nano
MedCode (Vals AI)30.4%Not measuredOnly GPT-5 Nano measured
MMLU Pro (Artificial Analysis run)78.0%74.8%GPT-5 Nano
SimpleQA Verified11.7%Not measuredOnly GPT-5 Nano measured
LMArena Text: science13181296GPT-5 Nano
LMArena Text: medicine and healthcare13351310GPT-5 Nano
LMArena Text: legal and government12981280GPT-5 Nano
LMArena Text: business and finance13111284GPT-5 Nano
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index20
Web design benchmarks for GPT-5 Nano and gpt-oss-20b
BenchmarkGPT-5 Nanogpt-oss-20bLeader
Design Arena: websites1101852GPT-5 Nano
Design Arena: UI components1064Not measuredOnly GPT-5 Nano measured
Design Arena: game dev1044Not measuredOnly GPT-5 Nano measured
Design Arena: data viz1056933GPT-5 Nano
Design Arena: 3D965Not measuredOnly GPT-5 Nano measured
Design Arena: all code categories1084Not measuredOnly GPT-5 Nano measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index173
General benchmarks for GPT-5 Nano and gpt-oss-20b
BenchmarkGPT-5 Nanogpt-oss-20bLeader
SAGE (Vals AI)30.4%Not measuredOnly GPT-5 Nano measured
MedScribe (Vals AI)72.9%Not measuredOnly GPT-5 Nano measured
IFBench67.6%65.1%GPT-5 Nano
Long context reasoning (AA-LCR)45.0%34.7%GPT-5 Nano
DTBench62.7%68.0%gpt-oss-20b
LMCA7.9%14.5%gpt-oss-20b
Fiction.LiveBench44.4%Not measuredOnly GPT-5 Nano measured
LMArena Text13201288GPT-5 Nano
LMArena Text: instruction following13061236GPT-5 Nano
LMArena Text: creative writing12491201GPT-5 Nano
LMArena Vision1159Not measuredOnly GPT-5 Nano measured
LMArena Text: English13211303GPT-5 Nano
LMArena Text: non-English13131269GPT-5 Nano
LMArena Text: Chinese13561315GPT-5 Nano
LMArena Text: German13271255GPT-5 Nano
LMArena Text: Japanese12271244gpt-oss-20b
LMArena Text: Korean12691236GPT-5 Nano
LMArena Text: Spanish13601267GPT-5 Nano
LMArena Text: Russian12961278GPT-5 Nano
LMArena Text: Polish13141252GPT-5 Nano
LMArena Text: multi-turn13111268GPT-5 Nano
LMArena Text: longer queries13121250GPT-5 Nano
LMArena Text: writing and language12831238GPT-5 Nano
LMArena Text: entertainment and media12681216GPT-5 Nano
LMArena Vision: English1170Not measuredOnly GPT-5 Nano measured
LMArena Vision: Chinese1176Not measuredOnly GPT-5 Nano measured
LMArena Vision: reading text1152Not measuredOnly GPT-5 Nano measured
LMArena Vision: humor1110Not measuredOnly GPT-5 Nano measured
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5 Nano and gpt-oss-20b
BenchmarkGPT-5 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 Nano$0.0003Fits 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 Nano$0.0037Fits 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 Nano$0.014Fits 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 Nano and gpt-oss-20b
SpecificationOpenAI GPT-5 NanoOpenAI gpt-oss-20b
MakerOpenAIOpenAI
WeightsNo public weights listedOpen weights
ReleasedAugust 7, 2025August 5, 2025
Context window400K131K
Input $/Mtok$0.05$0.03
Output $/Mtok$0.40$0.15
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved task$0.109Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 Nano better than gpt-oss-20b for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-5 Nano for a larger context window (400K against 131K tokens) and work measured by LiveCodeBench (Vals AI) or WeirdML, where it leads.

Which is cheaper, GPT-5 Nano or gpt-oss-20b?

GPT-5 Nano costs $0.05 per million input tokens and $0.40 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for GPT-5 Nano only.

Which has the bigger context window, GPT-5 Nano or gpt-oss-20b?

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

How many benchmarks is the GPT-5 Nano vs gpt-oss-20b comparison based on?

58 benchmarks have a result for both models as of October 22, 2026. GPT-5 Nano's coding index rests on 0 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