Enter opens the highlighted result. Esc closes.

DeepSeek V3 0324 vs gpt-oss-120b

gpt-oss-120b leads DeepSeek V3 0324 on the Artificial Analysis Intelligence Index, 11.6 to 9.7, and gpt-oss-120b costs 2.1x less per output token ($0.50 vs $1.07 per million). Updated October 22, 2026; 34 benchmarks have a result for both.

Replace DeepSeek V3 0324 Replace gpt-oss-120b
DeepSeek V3 0324DeepSeek
Coding
No data
Overall
No data
Output $/M
$1.07
7
gpt-oss-120bOpenAI
Coding
No data
Overall
50.0
Output $/M
$0.50
27
vs boards won of 34 shared

DeepSeek V3 0324 or gpt-oss-120b: which to pick

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

Pick DeepSeek V3 0324 for a larger context window (164K against 131K tokens) and work measured by AA Coding Index or LiveCodeBench (Vals AI), where it leads.

Model ADeepSeek V3 0324DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel Bgpt-oss-120bOpenAINot benchmarked1 independent benchmark$0.51 per solved task
Shared results
34
DeepSeek V3 0324 only
1
gpt-oss-120b only
47
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
DeepSeek V3 0324 not benchmarked, gpt-oss-120b not benchmarked.
Widest category
Math, 33.8 points apart on average over 6 shared benchmarks.
Widest single gap
AIME 2025 (Artificial Analysis run): DeepSeek V3 0324 41.0% against gpt-oss-120b 93.4%, 52.4 points apart on a 0 to 100 scale.
Output price
DeepSeek V3 0324 $1.07 against gpt-oss-120b $0.50 per million output tokens, 2.1x apart.
Context window
DeepSeek V3 0324 takes 164K tokens, gpt-oss-120b 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
CategoryDeepSeek V3 0324Barsgpt-oss-120bTies
Coding25
Intelligence01
Agentic work03
Reasoning14
Math06
Knowledge33
General15
All shared boards727
CodingLike-for-likeSix of these boards feed the Vibe Coding Index25
Coding benchmarks for DeepSeek V3 0324 and gpt-oss-120b
BenchmarkDeepSeek V3 0324gpt-oss-120bLeader
Aider polyglotNot measured41.8%Only gpt-oss-120b measured
SWE-bench Verified42.0%26.0%DeepSeek V3 0324
AA Coding Index21.230.4gpt-oss-120b
LiveCodeBench (Vals AI)65.5%83.2%gpt-oss-120b
SWE-bench Verified (Vals AI)Not measured33.6%Only gpt-oss-120b measured
LiveCodeBench (Artificial Analysis run)40.5%87.8%gpt-oss-120b
SciCode39.0%34.0%DeepSeek V3 0324
Terminal-Bench Hard (Artificial Analysis run)15.2%23.5%gpt-oss-120b
Terminal-BenchNot measured18.7%Only gpt-oss-120b measured
WeirdML36.1%48.2%gpt-oss-120b
ALE-BenchNot measured575.6Only gpt-oss-120b measured
LMArena Text: codingNot measured1379Only gpt-oss-120b measured
LMArena Text: software and ITNot measured1387Only gpt-oss-120b measured
SciCodeNot measured7.7%Only gpt-oss-120b measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3 0324 and gpt-oss-120b
BenchmarkDeepSeek V3 0324gpt-oss-120bLeader
AA Intelligence Index9.711.6gpt-oss-120b
Epoch Capabilities IndexNot measured139.8Only gpt-oss-120b measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index03
Agentic work benchmarks for DeepSeek V3 0324 and gpt-oss-120b
BenchmarkDeepSeek V3 0324gpt-oss-120bLeader
AA Agentic Index0.83.7gpt-oss-120b
τ²-Bench Telecom47.1%65.8%gpt-oss-120b
APEX-AgentsNot measured4.4%Only gpt-oss-120b measured
METR time horizons49.6%56.6%gpt-oss-120b
Vending-Bench 2Not measured-$22Only gpt-oss-120b measured
BrowseComp-PlusNot measured67.0%Only gpt-oss-120b measured
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
Reasoning benchmarks for DeepSeek V3 0324 and gpt-oss-120b
BenchmarkDeepSeek V3 0324gpt-oss-120bLeader
GPQA Diamond61.6%78.5%gpt-oss-120b
GPQA Diamond (Artificial Analysis run)65.5%78.2%gpt-oss-120b
Humanity's Last Exam (Artificial Analysis run)4.7%19.6%gpt-oss-120b
GPQA Diamond (Epoch AI run)67.6%75.8%gpt-oss-120b
SimpleBench27.2%22.1%DeepSeek V3 0324
Mystery game puzzlesNot measured2.0%Only gpt-oss-120b measured
LMArena Text: hard promptsNot measured1364Only gpt-oss-120b measured
LMArena Text: expertNot measured1356Only gpt-oss-120b measured
LMArena Text: hard prompts in EnglishNot measured1368Only gpt-oss-120b measured
Kagi LLM BenchmarkNot measured58.6%Only gpt-oss-120b measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for DeepSeek V3 0324 and gpt-oss-120b
BenchmarkDeepSeek V3 0324gpt-oss-120bLeader
AIME52.2%92.6%gpt-oss-120b
MATH 500 (Vals AI)88.6%94.8%gpt-oss-120b
MGSM (Vals AI)91.7%92.0%gpt-oss-120b
AA Math Index41.093.4gpt-oss-120b
AIME 2025 (Artificial Analysis run)41.0%93.4%gpt-oss-120b
OTIS Mock AIME37.8%88.9%gpt-oss-120b
MATH level 575.5%Not measuredOnly DeepSeek V3 0324 measured
LMArena Text: mathNot measured1389Only gpt-oss-120b measured
LMArena Text: mathematical workNot measured1386Only gpt-oss-120b measured
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index33
Knowledge benchmarks for DeepSeek V3 0324 and gpt-oss-120b
BenchmarkDeepSeek V3 0324gpt-oss-120bLeader
MMLU Pro79.5%79.2%DeepSeek V3 0324
LegalBench (Vals AI)77.7%75.9%DeepSeek V3 0324
CaseLaw (Vals AI)Not measured48.8%Only gpt-oss-120b measured
CorpFin (Vals AI)54.7%58.2%gpt-oss-120b
TaxEval (Vals AI)71.1%71.6%gpt-oss-120b
MedQA (Vals AI)82.0%91.4%gpt-oss-120b
MMLU Pro (Artificial Analysis run)81.9%80.8%DeepSeek V3 0324
LMArena Text: scienceNot measured1382Only gpt-oss-120b measured
LMArena Text: medicine and healthcareNot measured1388Only gpt-oss-120b measured
LMArena Text: legal and governmentNot measured1355Only gpt-oss-120b measured
LMArena Text: business and financeNot measured1359Only gpt-oss-120b measured
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for DeepSeek V3 0324 and gpt-oss-120b
BenchmarkDeepSeek V3 0324gpt-oss-120bLeader
Design Arena: websitesNot measured967Only gpt-oss-120b measured
Design Arena: UI componentsNot measured924Only gpt-oss-120b measured
Design Arena: game devNot measured992Only gpt-oss-120b measured
Design Arena: data vizNot measured987Only gpt-oss-120b measured
Design Arena: 3DNot measured901Only gpt-oss-120b measured
Design Arena: all code categoriesNot measured962Only 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 index15
General benchmarks for DeepSeek V3 0324 and gpt-oss-120b
BenchmarkDeepSeek V3 0324gpt-oss-120bLeader
IFBench41.0%69.0%gpt-oss-120b
Long context reasoning (AA-LCR)40.7%52.0%gpt-oss-120b
DTBench64.8%76.3%gpt-oss-120b
LMCA15.5%22.1%gpt-oss-120b
Fiction.LiveBench50.0%44.4%DeepSeek V3 0324
Creative writing (Lech Mazur)77.0%77.1%gpt-oss-120b
Surface Evolver BenchNot measured25.0%Only gpt-oss-120b measured
LMArena TextNot measured1366Only gpt-oss-120b measured
LMArena Text: instruction followingNot measured1318Only gpt-oss-120b measured
LMArena Text: creative writingNot measured1274Only gpt-oss-120b measured
LMArena Text: EnglishNot measured1375Only gpt-oss-120b measured
LMArena Text: non-EnglishNot measured1351Only gpt-oss-120b measured
LMArena Text: ChineseNot measured1385Only gpt-oss-120b measured
LMArena Text: GermanNot measured1353Only gpt-oss-120b measured
LMArena Text: JapaneseNot measured1331Only gpt-oss-120b measured
LMArena Text: KoreanNot measured1282Only gpt-oss-120b measured
LMArena Text: FrenchNot measured1370Only gpt-oss-120b measured
LMArena Text: SpanishNot measured1389Only gpt-oss-120b measured
LMArena Text: RussianNot measured1343Only gpt-oss-120b measured
LMArena Text: PolishNot measured1353Only gpt-oss-120b measured
LMArena Text: multi-turnNot measured1340Only gpt-oss-120b measured
LMArena Text: longer queriesNot measured1319Only gpt-oss-120b measured
LMArena Text: writing and languageNot measured1306Only gpt-oss-120b measured
LMArena Text: entertainment and mediaNot measured1292Only gpt-oss-120b measured
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 DeepSeek V3 0324 and gpt-oss-120b
BenchmarkDeepSeek V3 0324gpt-oss-120bLeader
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

DeepSeek V3 0324$0.0008Fits in one request
gpt-oss-120b$0.0003Fits in one request

gpt-oss-120b costs less

Repository review

50K input + 3K output tokens

DeepSeek V3 0324$0.017Fits in one request
gpt-oss-120b$0.0065Fits in one request

gpt-oss-120b costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3 0324$0.065Exceeds the context window
gpt-oss-120b$0.025Exceeds the context window

gpt-oss-120b 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 DeepSeek V3 0324 and gpt-oss-120b
SpecificationDeepSeek V3 0324OpenAI gpt-oss-120b
MakerDeepSeekOpenAI
WeightsOpen weightsOpen weights
ReleasedMarch 24, 2025August 5, 2025
Context window164K131K
Input $/Mtok$0.27$0.10
Output $/Mtok$1.07$0.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computable$0.51
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3 0324 better than gpt-oss-120b for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3 0324 for a larger context window (164K against 131K tokens) and work measured by AA Coding Index or LiveCodeBench (Vals AI), where it leads.

Which is cheaper, DeepSeek V3 0324 or gpt-oss-120b?

DeepSeek V3 0324 costs $0.27 per million input tokens and $1.07 per million output tokens; gpt-oss-120b costs $0.10 and $0.50. Cost per solved task is known for gpt-oss-120b only.

Which has the bigger context window, DeepSeek V3 0324 or gpt-oss-120b?

DeepSeek V3 0324, with 164K tokens against 131K.

How many benchmarks is the DeepSeek V3 0324 vs gpt-oss-120b comparison based on?

34 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3 0324's coding index rests on 0 independent benchmarks and gpt-oss-120b's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next