Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 Exp vs gpt-oss-20b

DeepSeek V3.2 Exp leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 16.6 to 10.0, and gpt-oss-20b costs 2.7x less per output token ($0.15 vs $0.41 per million). Updated October 22, 2026; 45 benchmarks have a result for both.

Replace DeepSeek V3.2 Exp Replace gpt-oss-20b
DeepSeek V3.2 ExpDeepSeek
Coding
No data
Overall
No data
Output $/M
$0.41
39
gpt-oss-20bOpenAI
Coding
No data
Overall
38.5
Output $/M
$0.15
6
vs boards won of 45 shared

DeepSeek V3.2 Exp or gpt-oss-20b: which to pick

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

Pick DeepSeek V3.2 Exp for a larger context window (164K against 131K tokens) and work measured by WeirdML or τ²-Bench Telecom, where it leads.

Model ADeepSeek V3.2 ExpDeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel Bgpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
45
DeepSeek V3.2 Exp only
14
gpt-oss-20b 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 Exp not benchmarked, gpt-oss-20b not benchmarked.
Widest category
Web design, 34.1 points apart on average over 2 shared benchmarks.
Widest single gap
Design Arena: websites: DeepSeek V3.2 Exp 1178 against gpt-oss-20b 852, 40.8 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 Exp $0.41 against gpt-oss-20b $0.15 per million output tokens, 2.7x apart.
Context window
DeepSeek V3.2 Exp takes 164K 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
CategoryDeepSeek V3.2 ExpBarsgpt-oss-20bTies
Coding41
Intelligence20
Agentic work01
Reasoning51
Math22
Knowledge50
Web design20
General191
All shared boards396
CodingLike-for-likeSix of these boards feed the Vibe Coding Index41
Coding benchmarks for DeepSeek V3.2 Exp and gpt-oss-20b
BenchmarkDeepSeek V3.2 Expgpt-oss-20bLeader
Aider polyglot74.2%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena WebDev1272Not measuredOnly DeepSeek V3.2 Exp measured
LiveCodeBench (Vals AI)Not measured80.4%Only gpt-oss-20b measured
LiveCodeBench (Artificial Analysis run)78.9%77.7%DeepSeek V3.2 Exp
SciCodeNot measured38.9%Only gpt-oss-20b measured
Terminal-Bench Hard (Artificial Analysis run)31.1%10.6%DeepSeek V3.2 Exp
Terminal-BenchNot measured3.4%Only gpt-oss-20b measured
WeirdML39.5%40.9%gpt-oss-20b
ALE-BenchNot measured566.0Only gpt-oss-20b measured
LMArena Text: coding14381307DeepSeek V3.2 Exp
LMArena Text: software and IT14381311DeepSeek V3.2 Exp
LMArena WebDev: HTML1281Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V3.2 Exp and gpt-oss-20b
BenchmarkDeepSeek V3.2 Expgpt-oss-20bLeader
AA Intelligence Index16.610.0DeepSeek V3.2 Exp
Epoch Capabilities Index144.9137.7DeepSeek V3.2 Exp
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3.2 Exp and gpt-oss-20b
BenchmarkDeepSeek V3.2 Expgpt-oss-20bLeader
τ²-Bench Telecom33.9%60.2%gpt-oss-20b
TheAgentCompany42.9%Not measuredOnly DeepSeek V3.2 Exp measured
Berkeley Function Calling Leaderboard (BFCL)56.7%Not measuredOnly DeepSeek V3.2 Exp measured
BrowseComp-PlusNot measured50.6%Only gpt-oss-20b measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index51
Reasoning benchmarks for DeepSeek V3.2 Exp and gpt-oss-20b
BenchmarkDeepSeek V3.2 Expgpt-oss-20bLeader
GPQA DiamondNot measured68.9%Only gpt-oss-20b measured
GPQA Diamond (Artificial Analysis run)79.7%68.8%DeepSeek V3.2 Exp
Humanity's Last Exam (Artificial Analysis run)14.9%11.0%DeepSeek V3.2 Exp
GPQA Diamond (Epoch AI run)Not measured60.8%Only gpt-oss-20b measured
LMArena Text: hard prompts14291274DeepSeek V3.2 Exp
LMArena Text: expert14221258DeepSeek V3.2 Exp
LMArena Text: hard prompts in English14441292DeepSeek V3.2 Exp
Kagi LLM Benchmark52.2%53.2%gpt-oss-20b
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for DeepSeek V3.2 Exp and gpt-oss-20b
BenchmarkDeepSeek V3.2 Expgpt-oss-20bLeader
AIMENot measured86.0%Only gpt-oss-20b measured
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 Index87.789.3gpt-oss-20b
AIME 2025 (Artificial Analysis run)87.7%89.3%gpt-oss-20b
OTIS Mock AIMENot measured65.3%Only gpt-oss-20b measured
LMArena Text: math14221317DeepSeek V3.2 Exp
LMArena Text: mathematical work14331305DeepSeek V3.2 Exp
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for DeepSeek V3.2 Exp and gpt-oss-20b
BenchmarkDeepSeek V3.2 Expgpt-oss-20bLeader
MMLU ProNot measured71.6%Only gpt-oss-20b measured
LegalBench (Vals AI)Not measured70.8%Only gpt-oss-20b measured
CaseLaw (Vals AI)Not measured43.8%Only gpt-oss-20b measured
CorpFin (Vals AI)Not measured53.1%Only gpt-oss-20b measured
TaxEval (Vals AI)Not measured63.7%Only gpt-oss-20b measured
MedQA (Vals AI)Not measured82.9%Only gpt-oss-20b measured
MMLU Pro (Artificial Analysis run)85.0%74.8%DeepSeek V3.2 Exp
LMArena Text: science14431296DeepSeek V3.2 Exp
LMArena Text: medicine and healthcare14681310DeepSeek V3.2 Exp
LMArena Text: legal and government14191280DeepSeek V3.2 Exp
LMArena Text: business and finance14121284DeepSeek V3.2 Exp
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index20
Web design benchmarks for DeepSeek V3.2 Exp and gpt-oss-20b
BenchmarkDeepSeek V3.2 Expgpt-oss-20bLeader
Design Arena: websites1178852DeepSeek V3.2 Exp
Design Arena: UI components1164Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: game dev1144Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: data viz1152933DeepSeek V3.2 Exp
Design Arena: 3D1148Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: all code categories1170Not measuredOnly DeepSeek V3.2 Exp measured
Design Arena: SVG1031Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index191
General benchmarks for DeepSeek V3.2 Exp and gpt-oss-20b
BenchmarkDeepSeek V3.2 Expgpt-oss-20bLeader
IFBench54.1%65.1%gpt-oss-20b
Long context reasoning (AA-LCR)72.3%34.7%DeepSeek V3.2 Exp
DTBench87.7%68.0%DeepSeek V3.2 Exp
LMCA29.1%14.5%DeepSeek V3.2 Exp
Fiction.LiveBench83.3%Not measuredOnly DeepSeek V3.2 Exp measured
CL-bench13.2%Not measuredOnly DeepSeek V3.2 Exp measured
CL-bench Life9.5%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text14251288DeepSeek V3.2 Exp
LMArena Text: instruction following14011236DeepSeek V3.2 Exp
LMArena Text: creative writing14041201DeepSeek V3.2 Exp
LMArena Text: English14411303DeepSeek V3.2 Exp
LMArena Text: non-English14041269DeepSeek V3.2 Exp
LMArena Text: Chinese14611315DeepSeek V3.2 Exp
LMArena Text: German14401255DeepSeek V3.2 Exp
LMArena Text: Japanese13311244DeepSeek V3.2 Exp
LMArena Text: Korean13721236DeepSeek V3.2 Exp
LMArena Text: French1434Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text: Spanish14411267DeepSeek V3.2 Exp
LMArena Text: Russian14121278DeepSeek V3.2 Exp
LMArena Text: Polish14351252DeepSeek V3.2 Exp
LMArena Text: multi-turn14221268DeepSeek V3.2 Exp
LMArena Text: longer queries14181250DeepSeek V3.2 Exp
LMArena Text: writing and language14071238DeepSeek V3.2 Exp
LMArena Text: entertainment and media14071216DeepSeek V3.2 Exp
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 V3.2 Exp and gpt-oss-20b
BenchmarkDeepSeek V3.2 Expgpt-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

DeepSeek V3.2 Exp$0.0005Fits in one request
gpt-oss-20b$0.0001Fits in one request

gpt-oss-20b costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2 Exp$0.015Fits in one request
gpt-oss-20b$0.0019Fits in one request

gpt-oss-20b costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2 Exp$0.058Exceeds the context window
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 DeepSeek V3.2 Exp and gpt-oss-20b
SpecificationDeepSeek V3.2 ExpOpenAI gpt-oss-20b
MakerDeepSeekOpenAI
WeightsOpen weightsOpen weights
ReleasedSeptember 29, 2025August 5, 2025
Context window164K131K
Input $/Mtok$0.27$0.03
Output $/Mtok$0.41$0.15
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 Exp better than gpt-oss-20b for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.2 Exp for a larger context window (164K against 131K tokens) and work measured by WeirdML or τ²-Bench Telecom, where it leads.

Which is cheaper, DeepSeek V3.2 Exp or gpt-oss-20b?

DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.2 Exp or gpt-oss-20b?

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

How many benchmarks is the DeepSeek V3.2 Exp vs gpt-oss-20b comparison based on?

45 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2 Exp's coding index rests on 1 independent benchmark 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