Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs Nemotron 3 Ultra

Nemotron 3 Ultra leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 22.9 to 10.0, and gpt-oss-20b costs 16.0x less per output token ($0.15 vs $2.40 per million). Updated October 22, 2026; 48 benchmarks have a result for both.

Replace gpt-oss-20b Replace Nemotron 3 Ultra
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
0
Nemotron 3 UltraNVIDIA
Coding
30.0
Overall
53.1
Output $/M
$2.40
48
vs boards won of 48 shared

gpt-oss-20b or Nemotron 3 Ultra: which to pick

Only Nemotron 3 Ultra has a coding score, 30.0 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 16.0x cheaper ($0.15 vs $2.40 per million).

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BNemotron 3 UltraNVIDIA30.0/1003 independent benchmarksNo cost per solved task
Shared results
48
gpt-oss-20b only
15
Nemotron 3 Ultra only
23
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-20b not benchmarked, Nemotron 3 Ultra 30.0 from 3 benchmarks.
Widest category
Web design, 31.3 points apart on average over 2 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): gpt-oss-20b 34.7% against Nemotron 3 Ultra 79.3%, 44.7 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against Nemotron 3 Ultra $2.40 per million output tokens, 16.0x apart.
Context window
gpt-oss-20b takes 131K tokens, Nemotron 3 Ultra 262K.

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-20bBarsNemotron 3 UltraTies
Coding06
Intelligence02
Agentic work01
Reasoning07
Math03
Knowledge08
Web design02
General019
All shared boards048
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
Coding benchmarks for gpt-oss-20b and Nemotron 3 Ultra
Benchmarkgpt-oss-20bNemotron 3 UltraLeader
AA Coding IndexNot measured49.3Only Nemotron 3 Ultra measured
LiveCodeBench (Vals AI)80.4%86.0%Nemotron 3 Ultra
SWE-bench Verified (Vals AI)Not measured69.0%Only Nemotron 3 Ultra measured
Vibe Code Bench (Vals AI)Not measured7.6%Only Nemotron 3 Ultra measured
Code migration (Vals AI)Not measured4.9%Only Nemotron 3 Ultra measured
ProgramBench (Vals AI)Not measured0.0%Only Nemotron 3 Ultra measured
Terminal-Bench 2.1 (Vals AI)Not measured50.9%Only Nemotron 3 Ultra measured
LiveCodeBench (Artificial Analysis run)77.7%Not measuredOnly gpt-oss-20b measured
SciCode38.9%40.3%Nemotron 3 Ultra
Terminal-Bench Hard (Artificial Analysis run)10.6%36.4%Nemotron 3 Ultra
Terminal-Bench3.4%Not measuredOnly gpt-oss-20b measured
FrontierCodeNot measured13.6%Only Nemotron 3 Ultra measured
WeirdML40.9%43.5%Nemotron 3 Ultra
ALE-Bench566.0Not measuredOnly gpt-oss-20b measured
LMArena Text: coding13071468Nemotron 3 Ultra
LMArena Text: software and IT13111468Nemotron 3 Ultra
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for gpt-oss-20b and Nemotron 3 Ultra
Benchmarkgpt-oss-20bNemotron 3 UltraLeader
AA Intelligence Index10.022.9Nemotron 3 Ultra
Epoch Capabilities Index137.7146.0Nemotron 3 Ultra
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for gpt-oss-20b and Nemotron 3 Ultra
Benchmarkgpt-oss-20bNemotron 3 UltraLeader
AA Agentic IndexNot measured20.1Only Nemotron 3 Ultra measured
Finance Agent (Vals AI)Not measured37.7%Only Nemotron 3 Ultra measured
Legal Research Bench (Vals AI)Not measured15.4%Only Nemotron 3 Ultra measured
Excel Modeling Benchmark (Vals AI)Not measured31.7%Only Nemotron 3 Ultra measured
τ²-Bench Telecom60.2%83.3%Nemotron 3 Ultra
APEX-AgentsNot measured22.7%Only Nemotron 3 Ultra measured
BrowseComp-Plus50.6%Not measuredOnly gpt-oss-20b measured
MCP AtlasNot measured63.1%Only Nemotron 3 Ultra measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
Reasoning benchmarks for gpt-oss-20b and Nemotron 3 Ultra
Benchmarkgpt-oss-20bNemotron 3 UltraLeader
GPQA Diamond68.9%86.1%Nemotron 3 Ultra
GPQA Diamond (Artificial Analysis run)68.8%86.7%Nemotron 3 Ultra
Humanity's Last Exam (Artificial Analysis run)11.0%28.4%Nemotron 3 Ultra
GPQA Diamond (Epoch AI run)60.8%85.4%Nemotron 3 Ultra
Mystery game puzzlesNot measured20.0%Only Nemotron 3 Ultra measured
LMArena Text: hard prompts12741452Nemotron 3 Ultra
LMArena Text: expert12581472Nemotron 3 Ultra
LMArena Text: hard prompts in English12921453Nemotron 3 Ultra
Kagi LLM Benchmark53.2%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for gpt-oss-20b and Nemotron 3 Ultra
Benchmarkgpt-oss-20bNemotron 3 UltraLeader
AIME86.0%Not measuredOnly gpt-oss-20b measured
MATH 500 (Vals AI)94.2%Not measuredOnly gpt-oss-20b measured
MGSM (Vals AI)89.0%Not measuredOnly gpt-oss-20b measured
AA Math Index89.3Not measuredOnly gpt-oss-20b measured
AIME 2025 (Artificial Analysis run)89.3%Not measuredOnly gpt-oss-20b measured
OTIS Mock AIME65.3%86.7%Nemotron 3 Ultra
ProofBenchNot measured2.0%Only Nemotron 3 Ultra measured
LMArena Text: math13171457Nemotron 3 Ultra
LMArena Text: mathematical work13051461Nemotron 3 Ultra
MathArena12.8%Not measuredOnly gpt-oss-20b measured
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index08
Knowledge benchmarks for gpt-oss-20b and Nemotron 3 Ultra
Benchmarkgpt-oss-20bNemotron 3 UltraLeader
MMLU Pro71.6%85.8%Nemotron 3 Ultra
LegalBench (Vals AI)70.8%82.1%Nemotron 3 Ultra
CaseLaw (Vals AI)43.8%Not measuredOnly gpt-oss-20b measured
CorpFin (Vals AI)53.1%65.5%Nemotron 3 Ultra
TaxEval (Vals AI)63.7%73.1%Nemotron 3 Ultra
MedQA (Vals AI)82.9%Not measuredOnly gpt-oss-20b measured
MedCode (Vals AI)Not measured38.6%Only Nemotron 3 Ultra measured
MMLU Pro (Artificial Analysis run)74.8%Not measuredOnly gpt-oss-20b measured
LMArena Text: science12961465Nemotron 3 Ultra
LMArena Text: medicine and healthcare13101456Nemotron 3 Ultra
LMArena Text: legal and government12801452Nemotron 3 Ultra
LMArena Text: business and finance12841434Nemotron 3 Ultra
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index02
Web design benchmarks for gpt-oss-20b and Nemotron 3 Ultra
Benchmarkgpt-oss-20bNemotron 3 UltraLeader
Design Arena: websites8521145Nemotron 3 Ultra
Design Arena: UI componentsNot measured1135Only Nemotron 3 Ultra measured
Design Arena: game devNot measured1138Only Nemotron 3 Ultra measured
Design Arena: data viz9331141Nemotron 3 Ultra
Design Arena: 3DNot measured1131Only Nemotron 3 Ultra measured
Design Arena: all code categoriesNot measured1146Only Nemotron 3 Ultra measured
Design Arena: SVGNot measured1069Only Nemotron 3 Ultra measured
Design Arena: ASCII artNot measured1100Only Nemotron 3 Ultra measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index019
General benchmarks for gpt-oss-20b and Nemotron 3 Ultra
Benchmarkgpt-oss-20bNemotron 3 UltraLeader
IFBench65.1%81.4%Nemotron 3 Ultra
Long context reasoning (AA-LCR)34.7%79.3%Nemotron 3 Ultra
DTBench68.0%90.1%Nemotron 3 Ultra
LMCA14.5%36.9%Nemotron 3 Ultra
LMArena Text12881445Nemotron 3 Ultra
LMArena Text: instruction following12361418Nemotron 3 Ultra
LMArena Text: creative writing12011399Nemotron 3 Ultra
LMArena Text: English13031455Nemotron 3 Ultra
LMArena Text: non-English12691427Nemotron 3 Ultra
LMArena Text: Chinese13151497Nemotron 3 Ultra
LMArena Text: German12551472Nemotron 3 Ultra
LMArena Text: Japanese1244Not measuredOnly gpt-oss-20b measured
LMArena Text: Korean12361384Nemotron 3 Ultra
LMArena Text: FrenchNot measured1472Only Nemotron 3 Ultra measured
LMArena Text: Spanish12671455Nemotron 3 Ultra
LMArena Text: Russian12781417Nemotron 3 Ultra
LMArena Text: Polish12521385Nemotron 3 Ultra
LMArena Text: multi-turn12681411Nemotron 3 Ultra
LMArena Text: longer queries12501437Nemotron 3 Ultra
LMArena Text: writing and language12381406Nemotron 3 Ultra
LMArena Text: entertainment and media12161397Nemotron 3 Ultra
Neither model has a result on the other 27 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for gpt-oss-20b and Nemotron 3 Ultra
Benchmarkgpt-oss-20bNemotron 3 UltraLeader
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-20b$0.0001Fits in one request
Nemotron 3 Ultra$0.0018Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
Nemotron 3 Ultra$0.037Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
Nemotron 3 Ultra$0.144Fits in one request

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-oss-20b and Nemotron 3 Ultra
SpecificationOpenAI gpt-oss-20bNVIDIA Nemotron 3 Ultra
MakerOpenAINVIDIA
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025June 4, 2026
Context window131K262K
Input $/Mtok$0.03$0.60
Output $/Mtok$0.15$2.40
Coding indexNot benchmarked30.0
Independent measurements behind it03
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-20b better than Nemotron 3 Ultra for coding?

Only Nemotron 3 Ultra has a coding score, 30.0 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 16.0x cheaper ($0.15 vs $2.40 per million).

Which is cheaper, gpt-oss-20b or Nemotron 3 Ultra?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Nemotron 3 Ultra costs $0.60 and $2.40. Cost per solved task is known for neither of them.

Which has the bigger context window, gpt-oss-20b or Nemotron 3 Ultra?

Nemotron 3 Ultra, with 262K tokens against 131K.

How many benchmarks is the gpt-oss-20b vs Nemotron 3 Ultra comparison based on?

48 benchmarks have a result for both models as of October 22, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and Nemotron 3 Ultra's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next