Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs gpt-oss-120b

DeepSeek V3.2 leads gpt-oss-120b on the Artificial Analysis Intelligence Index, 21.5 to 11.6, and gpt-oss-120b costs 1.8x less per output token ($0.50 vs $0.88 per million). Updated October 22, 2026; 64 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace gpt-oss-120b
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
55
gpt-oss-120bOpenAI
Coding
No data
Overall
50.0
Output $/M
$0.50
9
vs boards won of 64 shared

DeepSeek V3.2 or gpt-oss-120b: which to pick

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding.

Pick gpt-oss-120b for output tokens 1.8x cheaper ($0.50 vs $0.88 per million) and a lower cost per solved task ($0.51 against $0.99).

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel Bgpt-oss-120bOpenAINot benchmarked1 independent benchmark$0.51 per solved task
Shared results
64
DeepSeek V3.2 only
11
gpt-oss-120b only
17
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
DeepSeek V3.2 30.0 from 3 benchmarks, gpt-oss-120b not benchmarked.
Widest category
Web design, 24.4 points apart on average over 6 shared benchmarks.
Widest single gap
SWE-bench Verified: DeepSeek V3.2 70.0% against gpt-oss-120b 26.0%, 44.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against gpt-oss-120b $0.50 per million output tokens, 1.8x apart.
Context window
DeepSeek V3.2 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 V3.2Barsgpt-oss-120bTies
Coding72
Intelligence20
Agentic work30
Reasoning60
Math24
Knowledge92
Web design60
General201
All shared boards559
CodingLike-for-likeSix of these boards feed the Vibe Coding Index72
Coding benchmarks for DeepSeek V3.2 and gpt-oss-120b
BenchmarkDeepSeek V3.2gpt-oss-120bLeader
Aider polyglotNot measured41.8%Only gpt-oss-120b measured
SWE-bench Verified70.0%26.0%DeepSeek V3.2
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev1362Not measuredOnly DeepSeek V3.2 measured
AA Coding Index44.230.4DeepSeek V3.2
LiveCodeBench (Vals AI)80.7%83.2%gpt-oss-120b
SWE-bench Verified (Vals AI)67.6%33.6%DeepSeek V3.2
Vibe Code Bench (Vals AI)5.1%Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Artificial Analysis run)86.2%87.8%gpt-oss-120b
SciCodeNot measured34.0%Only gpt-oss-120b measured
Terminal-Bench Hard (Artificial Analysis run)35.6%23.5%DeepSeek V3.2
Terminal-Bench39.6%18.7%DeepSeek V3.2
WeirdMLNot measured48.2%Only gpt-oss-120b measured
ALE-BenchNot measured575.6Only gpt-oss-120b measured
LMArena Text: coding14531379DeepSeek V3.2
LMArena Text: software and IT14491387DeepSeek V3.2
LMArena WebDev: React1350Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev: HTML1371Not measuredOnly DeepSeek V3.2 measured
SciCodeNot measured7.7%Only gpt-oss-120b measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V3.2 and gpt-oss-120b
BenchmarkDeepSeek V3.2gpt-oss-120bLeader
AA Intelligence Index21.511.6DeepSeek V3.2
Epoch Capabilities Index146.1139.8DeepSeek V3.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
Agentic work benchmarks for DeepSeek V3.2 and gpt-oss-120b
BenchmarkDeepSeek V3.2gpt-oss-120bLeader
AA Agentic IndexNot measured3.7Only gpt-oss-120b measured
τ²-Bench Telecom90.6%65.8%DeepSeek V3.2
APEX-Agents21.3%4.4%DeepSeek V3.2
METR time horizonsNot measured56.6%Only gpt-oss-120b measured
Vending-Bench 2$1,034-$22DeepSeek V3.2
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 index60
Reasoning benchmarks for DeepSeek V3.2 and gpt-oss-120b
BenchmarkDeepSeek V3.2gpt-oss-120bLeader
GPQA Diamond80.3%78.5%DeepSeek V3.2
GPQA Diamond (Artificial Analysis run)84.0%78.2%DeepSeek V3.2
Humanity's Last Exam (Artificial Analysis run)24.6%19.6%DeepSeek V3.2
GPQA Diamond (Epoch AI run)Not measured75.8%Only gpt-oss-120b measured
ARC-AGI57.0%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI-24.0%Not measuredOnly DeepSeek V3.2 measured
SimpleBenchNot measured22.1%Only gpt-oss-120b measured
Mystery game puzzlesNot measured2.0%Only gpt-oss-120b measured
LMArena Text: hard prompts14341364DeepSeek V3.2
LMArena Text: expert14361356DeepSeek V3.2
LMArena Text: hard prompts in English14461368DeepSeek V3.2
Kagi LLM BenchmarkNot measured58.6%Only gpt-oss-120b measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for DeepSeek V3.2 and gpt-oss-120b
BenchmarkDeepSeek V3.2gpt-oss-120bLeader
AIME84.6%92.6%gpt-oss-120b
MATH 500 (Vals AI)Not measured94.8%Only gpt-oss-120b measured
MGSM (Vals AI)86.0%92.0%gpt-oss-120b
AA Math Index92.093.4gpt-oss-120b
AIME 2025 (Artificial Analysis run)92.0%93.4%gpt-oss-120b
OTIS Mock AIMENot measured88.9%Only gpt-oss-120b measured
LMArena Text: math14351389DeepSeek V3.2
LMArena Text: mathematical work14401386DeepSeek V3.2
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index92
Knowledge benchmarks for DeepSeek V3.2 and gpt-oss-120b
BenchmarkDeepSeek V3.2gpt-oss-120bLeader
MMLU Pro84.9%79.2%DeepSeek V3.2
LegalBench (Vals AI)76.1%75.9%DeepSeek V3.2
CaseLaw (Vals AI)55.4%48.8%DeepSeek V3.2
CorpFin (Vals AI)51.0%58.2%gpt-oss-120b
TaxEval (Vals AI)68.2%71.6%gpt-oss-120b
MedQA (Vals AI)93.9%91.4%DeepSeek V3.2
MMLU Pro (Artificial Analysis run)86.2%80.8%DeepSeek V3.2
LMArena Text: science14461382DeepSeek V3.2
LMArena Text: medicine and healthcare14401388DeepSeek V3.2
LMArena Text: legal and government14251355DeepSeek V3.2
LMArena Text: business and finance14101359DeepSeek V3.2
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for DeepSeek V3.2 and gpt-oss-120b
BenchmarkDeepSeek V3.2gpt-oss-120bLeader
Design Arena: websites1175967DeepSeek V3.2
Design Arena: UI components1146924DeepSeek V3.2
Design Arena: game dev1131992DeepSeek V3.2
Design Arena: data viz1158987DeepSeek V3.2
Design Arena: 3D1132901DeepSeek V3.2
Design Arena: all code categories1163962DeepSeek V3.2
Design Arena: SVG1032Not measuredOnly DeepSeek V3.2 measured
Design Arena: ASCII art1083Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index201
General benchmarks for DeepSeek V3.2 and gpt-oss-120b
BenchmarkDeepSeek V3.2gpt-oss-120bLeader
IFBench60.7%69.0%gpt-oss-120b
Long context reasoning (AA-LCR)73.3%52.0%DeepSeek V3.2
DTBench85.6%76.3%DeepSeek V3.2
LMCA28.8%22.1%DeepSeek V3.2
Fiction.LiveBenchNot measured44.4%Only gpt-oss-120b measured
Creative writing (Lech Mazur)Not measured77.1%Only gpt-oss-120b measured
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
Surface Evolver BenchNot measured25.0%Only gpt-oss-120b measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251366DeepSeek V3.2
LMArena Text: instruction following14131318DeepSeek V3.2
LMArena Text: creative writing14001274DeepSeek V3.2
LMArena Text: English14391375DeepSeek V3.2
LMArena Text: non-English14091351DeepSeek V3.2
LMArena Text: Chinese14551385DeepSeek V3.2
LMArena Text: German14131353DeepSeek V3.2
LMArena Text: Japanese13741331DeepSeek V3.2
LMArena Text: Korean13701282DeepSeek V3.2
LMArena Text: French14291370DeepSeek V3.2
LMArena Text: Spanish14241389DeepSeek V3.2
LMArena Text: Russian14241343DeepSeek V3.2
LMArena Text: Polish14191353DeepSeek V3.2
LMArena Text: multi-turn14271340DeepSeek V3.2
LMArena Text: longer queries14281319DeepSeek V3.2
LMArena Text: writing and language14071306DeepSeek V3.2
LMArena Text: entertainment and media13951292DeepSeek V3.2
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.2 and gpt-oss-120b
BenchmarkDeepSeek V3.2gpt-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 V3.2$0.0007Fits in one request
gpt-oss-120b$0.0003Fits in one request

gpt-oss-120b costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$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 V3.2$0.067Exceeds 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 V3.2 and gpt-oss-120b
SpecificationDeepSeek V3.2OpenAI gpt-oss-120b
MakerDeepSeekOpenAI
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025August 5, 2025
Context window164K131K
Input $/Mtok$0.29$0.10
Output $/Mtok$0.88$0.50
Coding index30.0Not benchmarked
Independent measurements behind it31
Cost per solved task$0.99$0.51
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than gpt-oss-120b for coding?

Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; gpt-oss-120b has none, so the two cannot be ranked on coding. Pick gpt-oss-120b for output tokens 1.8x cheaper ($0.50 vs $0.88 per million) and a lower cost per solved task ($0.51 against $0.99).

Which is cheaper, DeepSeek V3.2 or gpt-oss-120b?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; gpt-oss-120b costs $0.10 and $0.50. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and gpt-oss-120b $0.51.

Which has the bigger context window, DeepSeek V3.2 or gpt-oss-120b?

DeepSeek V3.2, with 164K tokens against 131K.

How many benchmarks is the DeepSeek V3.2 vs gpt-oss-120b comparison based on?

64 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 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