Enter opens the highlighted result. Esc closes.

gpt-oss-20b vs Phi 4

Updated October 21, 2026. 40 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace gpt-oss-20b Replace Phi 4
gpt-oss-20bOpenAI
Coding
No data
Overall
10.0
Output $/M
$0.15
40
Phi 4Microsoft
Coding
No data
Overall
5.9
Output $/M
$0.14
0
vs boards won of 40 shared

Decision reading

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

gpt-oss-20b has the edge where the context window is larger, 131K against 16K tokens.

Model Agpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BPhi 4MicrosoftNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
40
gpt-oss-20b only
20
Phi 4 only
5
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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, Phi 4 not benchmarked.
Widest category
Agentic work, 60.2 points apart on average over 1 shared benchmark.
Widest single gap
AIME 2025 (Artificial Analysis run): gpt-oss-20b 89.3% against Phi 4 18.0%, 71.3 points apart on a 0 to 100 scale.
Output price
gpt-oss-20b $0.15 against Phi 4 $0.14 per million output tokens, 1.1x apart.
Context window
gpt-oss-20b takes 131K tokens, Phi 4 16K.

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-20bBarsPhi 4Ties
Coding40
Intelligence20
Agentic work10
Reasoning60
Math50
Knowledge50
General170
All shared boards400
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for gpt-oss-20b and Phi 4
Benchmarkgpt-oss-20bPhi 4Leader
LiveCodeBench (Vals AI)80.4%Not measuredOnly gpt-oss-20b measured
LiveCodeBench (Artificial Analysis run)77.7%23.1%gpt-oss-20b
SciCode38.9%Not measuredOnly gpt-oss-20b measured
Terminal-Bench Hard (Artificial Analysis run)10.6%3.8%gpt-oss-20b
Terminal-Bench3.4%Not measuredOnly gpt-oss-20b measured
WeirdML40.9%Not measuredOnly gpt-oss-20b measured
ALE-Bench566.0Not measuredOnly gpt-oss-20b measured
LMArena Text: coding13071231gpt-oss-20b
LMArena Text: software and IT13111228gpt-oss-20b
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-oss-20b and Phi 4
Benchmarkgpt-oss-20bPhi 4Leader
AA Intelligence Index10.05.9gpt-oss-20b
Epoch Capabilities Index137.7130.5gpt-oss-20b
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for gpt-oss-20b and Phi 4
Benchmarkgpt-oss-20bPhi 4Leader
τ²-Bench Telecom60.2%0.0%gpt-oss-20b
BALROGNot measured11.6%Only Phi 4 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for gpt-oss-20b and Phi 4
Benchmarkgpt-oss-20bPhi 4Leader
GPQA Diamond68.9%Not measuredOnly gpt-oss-20b measured
GPQA Diamond (Artificial Analysis run)68.8%57.5%gpt-oss-20b
Humanity's Last Exam (Artificial Analysis run)11.0%3.8%gpt-oss-20b
GPQA Diamond (Epoch AI run)60.8%56.1%gpt-oss-20b
LMArena Text: hard prompts12741220gpt-oss-20b
LMArena Text: expert12581203gpt-oss-20b
LMArena Text: hard prompts in English12921230gpt-oss-20b
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for gpt-oss-20b and Phi 4
Benchmarkgpt-oss-20bPhi 4Leader
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 Index89.318.0gpt-oss-20b
AIME 2025 (Artificial Analysis run)89.3%18.0%gpt-oss-20b
OTIS Mock AIME65.3%13.8%gpt-oss-20b
MATH level 5Not measured64.9%Only Phi 4 measured
LMArena Text: math13171246gpt-oss-20b
LMArena Text: mathematical work13051254gpt-oss-20b
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for gpt-oss-20b and Phi 4
Benchmarkgpt-oss-20bPhi 4Leader
MMLU Pro71.6%Not measuredOnly gpt-oss-20b measured
LegalBench (Vals AI)70.8%Not measuredOnly gpt-oss-20b measured
CaseLaw (Vals AI)43.8%Not measuredOnly gpt-oss-20b measured
CorpFin (Vals AI)53.1%Not measuredOnly gpt-oss-20b measured
TaxEval (Vals AI)63.7%Not measuredOnly gpt-oss-20b measured
MedQA (Vals AI)82.9%Not measuredOnly gpt-oss-20b measured
MMLU Pro (Artificial Analysis run)74.8%71.4%gpt-oss-20b
MMLUNot measured84.8%Only Phi 4 measured
LMArena Text: science12961206gpt-oss-20b
LMArena Text: medicine and healthcare13101202gpt-oss-20b
LMArena Text: legal and government12801241gpt-oss-20b
LMArena Text: business and finance12841199gpt-oss-20b
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-oss-20b and Phi 4
Benchmarkgpt-oss-20bPhi 4Leader
Design Arena: websites853Not measuredOnly gpt-oss-20b measured
Design Arena: data viz933Not measuredOnly 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 index170
General benchmarks for gpt-oss-20b and Phi 4
Benchmarkgpt-oss-20bPhi 4Leader
IFBench65.1%23.5%gpt-oss-20b
Long context reasoning (AA-LCR)34.7%0.0%gpt-oss-20b
DTBench68.0%Not measuredOnly gpt-oss-20b measured
LMCA14.5%Not measuredOnly gpt-oss-20b measured
Creative writing (Lech Mazur)Not measured62.6%Only Phi 4 measured
LMArena Text12881217gpt-oss-20b
LMArena Text: instruction following12361201gpt-oss-20b
LMArena Text: creative writing12011181gpt-oss-20b
LMArena Text: English13031231gpt-oss-20b
LMArena Text: non-English12691197gpt-oss-20b
LMArena Text: Chinese13151212gpt-oss-20b
LMArena Text: German12551222gpt-oss-20b
LMArena Text: Japanese12441158gpt-oss-20b
LMArena Text: Korean12361151gpt-oss-20b
LMArena Text: FrenchNot measured1224Only Phi 4 measured
LMArena Text: Spanish12671234gpt-oss-20b
LMArena Text: Russian12781209gpt-oss-20b
LMArena Text: Polish1252Not measuredOnly gpt-oss-20b measured
LMArena Text: multi-turn12681206gpt-oss-20b
LMArena Text: longer queries12501217gpt-oss-20b
LMArena Text: writing and language12381198gpt-oss-20b
LMArena Text: entertainment and media12161162gpt-oss-20b
Neither model has a result on the other 24 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 Phi 4
Benchmarkgpt-oss-20bPhi 4Leader
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
Phi 4$0.0001Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

gpt-oss-20b$0.0019Fits in one request
Phi 4$0.0039Exceeds the context window

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

gpt-oss-20b$0.0075Exceeds the context window
Phi 4$0.015Exceeds 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-oss-20b and Phi 4
SpecificationOpenAI gpt-oss-20bMicrosoft Phi 4
MakerOpenAIMicrosoft
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025January 10, 2025
Context window131K16K
Input $/Mtok$0.03$0.07
Output $/Mtok$0.15$0.14
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-20b better than Phi 4 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. gpt-oss-20b has the edge where the context window is larger, 131K against 16K tokens.

Which is cheaper, gpt-oss-20b or Phi 4?

gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for neither of them.

Which has the bigger context window, gpt-oss-20b or Phi 4?

gpt-oss-20b, with 131K tokens against 16K.

How many benchmarks is the gpt-oss-20b vs Phi 4 comparison based on?

40 benchmarks have a result for both models as of October 21, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and Phi 4's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next