Enter opens the highlighted result. Esc closes.

gpt-oss-120b vs Phi 4

Updated October 21, 2026. 42 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace gpt-oss-120b Replace Phi 4
gpt-oss-120bOpenAI
Coding
No data
Overall
11.6
Output $/M
$0.50
42
Phi 4Microsoft
Coding
No data
Overall
5.9
Output $/M
$0.14
0
vs boards won of 42 shared

Decision reading

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

gpt-oss-120b has the edge where the context window is larger, 131K against 16K tokens.

Model Agpt-oss-120bOpenAINot benchmarked1 independent benchmark$0.51 per solved taskModel BPhi 4MicrosoftNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
42
gpt-oss-120b only
36
Phi 4 only
3
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-120b not benchmarked, Phi 4 not benchmarked.
Widest category
Agentic work, 65.8 points apart on average over 1 shared benchmark.
Widest single gap
AIME 2025 (Artificial Analysis run): gpt-oss-120b 93.4% against Phi 4 18.0%, 75.4 points apart on a 0 to 100 scale.
Output price
gpt-oss-120b $0.50 against Phi 4 $0.14 per million output tokens, 3.6x apart.
Context window
gpt-oss-120b 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-120bBarsPhi 4Ties
Coding40
Intelligence20
Agentic work10
Reasoning60
Math50
Knowledge50
General190
All shared boards420
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for gpt-oss-120b and Phi 4
Benchmarkgpt-oss-120bPhi 4Leader
Aider polyglot41.8%Not measuredOnly gpt-oss-120b measured
SWE-bench Verified26.0%Not measuredOnly gpt-oss-120b measured
AA Coding Index30.4Not measuredOnly gpt-oss-120b measured
LiveCodeBench (Vals AI)83.2%Not measuredOnly gpt-oss-120b measured
SWE-bench Verified (Vals AI)33.6%Not measuredOnly gpt-oss-120b measured
LiveCodeBench (Artificial Analysis run)87.8%23.1%gpt-oss-120b
SciCode34.0%Not measuredOnly gpt-oss-120b measured
Terminal-Bench Hard (Artificial Analysis run)23.5%3.8%gpt-oss-120b
Terminal-Bench18.7%Not measuredOnly gpt-oss-120b measured
WeirdML48.2%Not measuredOnly gpt-oss-120b measured
ALE-Bench575.6Not measuredOnly gpt-oss-120b measured
LMArena Text: coding13791231gpt-oss-120b
LMArena Text: software and IT13871228gpt-oss-120b
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-oss-120b and Phi 4
Benchmarkgpt-oss-120bPhi 4Leader
AA Intelligence Index11.65.9gpt-oss-120b
Epoch Capabilities Index139.8130.5gpt-oss-120b
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for gpt-oss-120b and Phi 4
Benchmarkgpt-oss-120bPhi 4Leader
AA Agentic Index3.7Not measuredOnly gpt-oss-120b measured
τ²-Bench Telecom65.8%0.0%gpt-oss-120b
APEX-Agents4.4%Not measuredOnly gpt-oss-120b measured
METR time horizons56.6%Not measuredOnly gpt-oss-120b measured
BALROGNot measured11.6%Only Phi 4 measured
Vending-Bench 2-$22Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 33 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for gpt-oss-120b and Phi 4
Benchmarkgpt-oss-120bPhi 4Leader
GPQA Diamond78.5%Not measuredOnly gpt-oss-120b measured
GPQA Diamond (Artificial Analysis run)78.2%57.5%gpt-oss-120b
Humanity's Last Exam (Artificial Analysis run)19.6%3.8%gpt-oss-120b
GPQA Diamond (Epoch AI run)75.8%56.1%gpt-oss-120b
SimpleBench22.1%Not measuredOnly gpt-oss-120b measured
Mystery game puzzles2.0%Not measuredOnly gpt-oss-120b measured
LMArena Text: hard prompts13641220gpt-oss-120b
LMArena Text: expert13561203gpt-oss-120b
LMArena Text: hard prompts in English13681230gpt-oss-120b
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for gpt-oss-120b and Phi 4
Benchmarkgpt-oss-120bPhi 4Leader
AIME92.6%Not measuredOnly gpt-oss-120b measured
MATH 500 (Vals AI)94.8%Not measuredOnly gpt-oss-120b measured
MGSM (Vals AI)92.0%Not measuredOnly gpt-oss-120b measured
AA Math Index93.418.0gpt-oss-120b
AIME 2025 (Artificial Analysis run)93.4%18.0%gpt-oss-120b
OTIS Mock AIME88.9%13.8%gpt-oss-120b
MATH level 5Not measured64.9%Only Phi 4 measured
LMArena Text: math13891246gpt-oss-120b
LMArena Text: mathematical work13861254gpt-oss-120b
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-120b and Phi 4
Benchmarkgpt-oss-120bPhi 4Leader
MMLU Pro79.2%Not measuredOnly gpt-oss-120b measured
LegalBench (Vals AI)75.9%Not measuredOnly gpt-oss-120b measured
CaseLaw (Vals AI)48.8%Not measuredOnly gpt-oss-120b measured
CorpFin (Vals AI)58.2%Not measuredOnly gpt-oss-120b measured
TaxEval (Vals AI)71.6%Not measuredOnly gpt-oss-120b measured
MedQA (Vals AI)91.4%Not measuredOnly gpt-oss-120b measured
MMLU Pro (Artificial Analysis run)80.8%71.4%gpt-oss-120b
MMLUNot measured84.8%Only Phi 4 measured
LMArena Text: science13821206gpt-oss-120b
LMArena Text: medicine and healthcare13881202gpt-oss-120b
LMArena Text: legal and government13551241gpt-oss-120b
LMArena Text: business and finance13591199gpt-oss-120b
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for gpt-oss-120b and Phi 4
Benchmarkgpt-oss-120bPhi 4Leader
Design Arena: websites968Not measuredOnly gpt-oss-120b measured
Design Arena: UI components927Not measuredOnly gpt-oss-120b measured
Design Arena: game dev992Not measuredOnly gpt-oss-120b measured
Design Arena: data viz987Not measuredOnly gpt-oss-120b measured
Design Arena: 3D901Not measuredOnly gpt-oss-120b measured
Design Arena: all code categories963Not measuredOnly gpt-oss-120b measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for gpt-oss-120b and Phi 4
Benchmarkgpt-oss-120bPhi 4Leader
IFBench69.0%23.5%gpt-oss-120b
Long context reasoning (AA-LCR)52.0%0.0%gpt-oss-120b
DTBench76.3%Not measuredOnly gpt-oss-120b measured
LMCA22.1%Not measuredOnly gpt-oss-120b measured
Fiction.LiveBench44.4%Not measuredOnly gpt-oss-120b measured
Creative writing (Lech Mazur)77.1%62.6%gpt-oss-120b
Surface Evolver Bench25.0%Not measuredOnly gpt-oss-120b measured
LMArena Text13661217gpt-oss-120b
LMArena Text: instruction following13181201gpt-oss-120b
LMArena Text: creative writing12741181gpt-oss-120b
LMArena Text: English13751231gpt-oss-120b
LMArena Text: non-English13511197gpt-oss-120b
LMArena Text: Chinese13851212gpt-oss-120b
LMArena Text: German13531222gpt-oss-120b
LMArena Text: Japanese13311158gpt-oss-120b
LMArena Text: Korean12821151gpt-oss-120b
LMArena Text: French13701224gpt-oss-120b
LMArena Text: Spanish13891234gpt-oss-120b
LMArena Text: Russian13431209gpt-oss-120b
LMArena Text: Polish1353Not measuredOnly gpt-oss-120b measured
LMArena Text: multi-turn13401206gpt-oss-120b
LMArena Text: longer queries13191217gpt-oss-120b
LMArena Text: writing and language13061198gpt-oss-120b
LMArena Text: entertainment and media12921162gpt-oss-120b
Neither model has a result on the other 22 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for gpt-oss-120b and Phi 4
Benchmarkgpt-oss-120bPhi 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-120b$0.0003Fits in one request
Phi 4$0.0001Fits in one request

Phi 4 costs less

Repository review

50K input + 3K output tokens

gpt-oss-120b$0.0065Fits in one request
Phi 4$0.0039Exceeds the context window

Phi 4 costs less

Agent loop

200K input + 10K output tokens

gpt-oss-120b$0.025Exceeds the context window
Phi 4$0.015Exceeds the context window

Phi 4 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-120b and Phi 4
SpecificationOpenAI gpt-oss-120bMicrosoft Phi 4
MakerOpenAIMicrosoft
WeightsOpen weightsOpen weights
ReleasedAugust 5, 2025January 10, 2025
Context window131K16K
Input $/Mtok$0.10$0.07
Output $/Mtok$0.50$0.14
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved task$0.51Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is gpt-oss-120b better than Phi 4 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. gpt-oss-120b has the edge where the context window is larger, 131K against 16K tokens.

Which is cheaper, gpt-oss-120b or Phi 4?

gpt-oss-120b costs $0.10 per million input tokens and $0.50 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for gpt-oss-120b only.

Which has the bigger context window, gpt-oss-120b or Phi 4?

gpt-oss-120b, with 131K tokens against 16K.

How many benchmarks is the gpt-oss-120b vs Phi 4 comparison based on?

42 benchmarks have a result for both models as of October 21, 2026. gpt-oss-120b's coding index rests on 1 independent benchmark and Phi 4's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next