Enter opens the highlighted result. Esc closes.

GPT-5.4 Mini vs gpt-oss-20b

GPT-5.4 Mini leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 24.1 to 10.0, and gpt-oss-20b costs 30.0x less per output token ($0.15 vs $4.50 per million). Updated October 21, 2026; 50 benchmarks have a result for both.

Replace GPT-5.4 Mini Replace gpt-oss-20b
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
49
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
1
vs boards won of 50 shared

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

Only GPT-5.4 Mini has a coding score, 35.8 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 30.0x cheaper ($0.15 vs $4.50 per million) and work measured by Kagi LLM Benchmark, where it leads.

Model AGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved taskModel Bgpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
50
GPT-5.4 Mini only
39
gpt-oss-20b only
12
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 Mini 35.8 from 5 benchmarks, gpt-oss-20b not benchmarked.
Widest category
General, 23.8 points apart on average over 20 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): GPT-5.4 Mini 77.0% against gpt-oss-20b 34.7%, 42.3 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Mini $4.50 against gpt-oss-20b $0.15 per million output tokens, 30.0x apart.
Context window
GPT-5.4 Mini 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 MiniBarsgpt-oss-20bTies
Coding70
Intelligence20
Agentic work10
Reasoning71
Math40
Knowledge80
General200
All shared boards491
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
Coding benchmarks for GPT-5.4 Mini and gpt-oss-20b
BenchmarkGPT-5.4 Minigpt-oss-20bLeader
LMArena WebDev1397Not measuredOnly GPT-5.4 Mini measured
AA Coding Index56.1Not measuredOnly GPT-5.4 Mini measured
LiveCodeBench (Vals AI)81.5%80.4%GPT-5.4 Mini
SWE-bench Verified (Vals AI)73.0%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench 4 (Vals AI)2.5%Not measuredOnly GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)48.0%Not measuredOnly GPT-5.4 Mini measured
Code migration (Vals AI)12.9%Not measuredOnly GPT-5.4 Mini measured
ProgramBench (Vals AI)0.0%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench 2.1 (Vals AI)54.7%Not measuredOnly GPT-5.4 Mini measured
LiveCodeBench (Artificial Analysis run)Not measured77.7%Only gpt-oss-20b measured
SciCode52.1%38.9%GPT-5.4 Mini
Terminal-Bench Hard (Artificial Analysis run)52.3%10.6%GPT-5.4 Mini
Terminal-BenchNot measured3.4%Only gpt-oss-20b measured
FrontierCode27.0%Not measuredOnly GPT-5.4 Mini measured
WeirdML60.3%40.9%GPT-5.4 Mini
ALE-Bench1188.6566.0GPT-5.4 Mini
LMArena Text: coding14381307GPT-5.4 Mini
LMArena Text: software and IT14361311GPT-5.4 Mini
LMArena WebDev: React1386Not measuredOnly GPT-5.4 Mini measured
LMArena WebDev: HTML1419Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.4 Mini and gpt-oss-20b
BenchmarkGPT-5.4 Minigpt-oss-20bLeader
AA Intelligence Index24.110.0GPT-5.4 Mini
Epoch Capabilities Index148.7137.7GPT-5.4 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5.4 Mini and gpt-oss-20b
BenchmarkGPT-5.4 Minigpt-oss-20bLeader
AA Agentic Index17.9Not measuredOnly GPT-5.4 Mini measured
Finance Agent (Vals AI)45.4%Not measuredOnly GPT-5.4 Mini measured
Tax Agent Bench (Vals AI)8.8%Not measuredOnly GPT-5.4 Mini measured
Legal Research Bench (Vals AI)12.5%Not measuredOnly GPT-5.4 Mini measured
Excel Modeling Benchmark (Vals AI)45.4%Not measuredOnly GPT-5.4 Mini measured
τ²-Bench Telecom83.3%60.2%GPT-5.4 Mini
DeepResearch Bench36.3%Not measuredOnly GPT-5.4 Mini measured
BrowseComp-PlusNot measured50.6%Only gpt-oss-20b measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index71
Reasoning benchmarks for GPT-5.4 Mini and gpt-oss-20b
BenchmarkGPT-5.4 Minigpt-oss-20bLeader
GPQA Diamond83.1%68.9%GPT-5.4 Mini
MMMU Pro (Vals AI)79.3%Not measuredOnly GPT-5.4 Mini measured
GPQA Diamond (Artificial Analysis run)87.5%68.8%GPT-5.4 Mini
Humanity's Last Exam (Artificial Analysis run)28.1%11.0%GPT-5.4 Mini
GPQA Diamond (Epoch AI run)86.9%60.8%GPT-5.4 Mini
ARC-AGI63.7%Not measuredOnly GPT-5.4 Mini measured
ARC-AGI-218.9%Not measuredOnly GPT-5.4 Mini measured
Chess puzzles23.0%Not measuredOnly GPT-5.4 Mini measured
Mystery game puzzles11.0%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: hard prompts14241274GPT-5.4 Mini
LMArena Text: expert14351258GPT-5.4 Mini
LMArena Text: hard prompts in English14201292GPT-5.4 Mini
LMArena Vision: diagrams1266Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: homework1285Not measuredOnly GPT-5.4 Mini measured
Kagi LLM Benchmark37.9%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 Mini and gpt-oss-20b
BenchmarkGPT-5.4 Minigpt-oss-20bLeader
AIME95.6%86.0%GPT-5.4 Mini
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 AIME88.9%65.3%GPT-5.4 Mini
FrontierMath, tiers 1 to 351.2%Not measuredOnly GPT-5.4 Mini measured
FrontierMath, tier 49.8%Not measuredOnly GPT-5.4 Mini measured
ProofBench21.0%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: math14181317GPT-5.4 Mini
LMArena Text: mathematical work14291305GPT-5.4 Mini
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index80
Knowledge benchmarks for GPT-5.4 Mini and gpt-oss-20b
BenchmarkGPT-5.4 Minigpt-oss-20bLeader
MMLU Pro84.5%71.6%GPT-5.4 Mini
LegalBench (Vals AI)Not measured70.8%Only gpt-oss-20b measured
CaseLaw (Vals AI)51.7%43.8%GPT-5.4 Mini
CorpFin (Vals AI)60.9%53.1%GPT-5.4 Mini
TaxEval (Vals AI)71.2%63.7%GPT-5.4 Mini
MortgageTax (Vals AI)63.5%Not measuredOnly GPT-5.4 Mini measured
MedQA (Vals AI)Not measured82.9%Only gpt-oss-20b measured
MMLU Pro (Artificial Analysis run)Not measured74.8%Only gpt-oss-20b measured
SimpleQA Verified29.4%Not measuredOnly GPT-5.4 Mini measured
LMArena Text: science14171296GPT-5.4 Mini
LMArena Text: medicine and healthcare13951310GPT-5.4 Mini
LMArena Text: legal and government14141280GPT-5.4 Mini
LMArena Text: business and finance14181284GPT-5.4 Mini
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Web design benchmarks for GPT-5.4 Mini and gpt-oss-20b
BenchmarkGPT-5.4 Minigpt-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 Mini and gpt-oss-20b
BenchmarkGPT-5.4 Minigpt-oss-20bLeader
SAGE (Vals AI)50.8%Not measuredOnly GPT-5.4 Mini measured
Vals Multimodal Index54.2%Not measuredOnly GPT-5.4 Mini measured
IFBench73.3%65.1%GPT-5.4 Mini
Long context reasoning (AA-LCR)77.0%34.7%GPT-5.4 Mini
DTBench80.0%68.0%GPT-5.4 Mini
LMCA40.8%14.5%GPT-5.4 Mini
LMArena Text14121288GPT-5.4 Mini
LMArena Text: instruction following14051236GPT-5.4 Mini
LMArena Text: creative writing13701201GPT-5.4 Mini
LMArena Vision1245Not measuredOnly GPT-5.4 Mini measured
LMArena Text: English14121303GPT-5.4 Mini
LMArena Text: non-English14051269GPT-5.4 Mini
LMArena Text: Chinese14461315GPT-5.4 Mini
LMArena Text: German14081255GPT-5.4 Mini
LMArena Text: Japanese13751244GPT-5.4 Mini
LMArena Text: Korean13701236GPT-5.4 Mini
LMArena Text: French1441Not measuredOnly GPT-5.4 Mini measured
LMArena Text: Spanish14051267GPT-5.4 Mini
LMArena Text: Russian14171278GPT-5.4 Mini
LMArena Text: Polish14151252GPT-5.4 Mini
LMArena Text: multi-turn14291268GPT-5.4 Mini
LMArena Text: longer queries14081250GPT-5.4 Mini
LMArena Text: writing and language13931238GPT-5.4 Mini
LMArena Text: entertainment and media13731216GPT-5.4 Mini
LMArena Vision: English1244Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: Chinese1286Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: reading text1253Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: humor1235Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: recognizing things1218Not measuredOnly GPT-5.4 Mini measured
LMArena Vision: creative writing1222Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.4 Mini and gpt-oss-20b
BenchmarkGPT-5.4 Minigpt-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 Mini$0.0030Fits 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 Mini$0.051Fits 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 Mini$0.195Fits 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 Mini and gpt-oss-20b
SpecificationOpenAI GPT-5.4 MiniOpenAI gpt-oss-20b
MakerOpenAIOpenAI
WeightsNo public weights listedOpen weights
ReleasedMarch 17, 2026August 5, 2025
Context window400K131K
Input $/Mtok$0.75$0.03
Output $/Mtok$4.50$0.15
Coding index35.8Not benchmarked
Independent measurements behind it50
Cost per solved task$0.70Not computable
SourceOpenRouter listingOpenRouter listing

Questions

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

Only GPT-5.4 Mini has a coding score, 35.8 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 30.0x cheaper ($0.15 vs $4.50 per million) and work measured by Kagi LLM Benchmark, where it leads.

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

GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for GPT-5.4 Mini only.

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

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

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

50 benchmarks have a result for both models as of October 21, 2026. GPT-5.4 Mini's coding index rests on 5 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