Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs GPT-5 Mini

GPT-5 Mini leads DeepSeek V3.2 on coding, 34.2 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 2.3x less per output token ($0.88 vs $2.00 per million). Updated October 22, 2026; 68 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace GPT-5 Mini
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
53
GPT-5 MiniOpenAI
Coding
34.2
Overall
43.7
Output $/M
$2.00
14
vs boards won of 68 shared, 1 tied

DeepSeek V3.2 or GPT-5 Mini: which to pick

Pick GPT-5 Mini for coding: it scores 34.2 on the Vibe Coding Index against 30.0 for DeepSeek V3.2, though on 2 benchmarks against 3.

Pick DeepSeek V3.2 for output tokens 2.3x cheaper ($0.88 vs $2.00 per million) and work measured by SWE-bench Verified or SWE-bench Multilingual, where it leads.

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved task
Shared results
68
DeepSeek V3.2 only
7
GPT-5 Mini only
33
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-5 Mini 34.2 from 2 benchmarks.
Widest category
Agentic work, 13.0 points apart on average over 2 shared benchmarks.
Widest single gap
τ²-Bench Telecom: DeepSeek V3.2 90.6% against GPT-5 Mini 71.1%, 19.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against GPT-5 Mini $2.00 per million output tokens, 2.3x apart.
Context window
DeepSeek V3.2 takes 164K tokens, GPT-5 Mini 400K.

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-5 MiniTies
Coding82
Intelligence20
Agentic work20
Reasoning611 tie
Math42
Knowledge65
Web design62
General192
All shared boards53141 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index82
Coding benchmarks for DeepSeek V3.2 and GPT-5 Mini
BenchmarkDeepSeek V3.2GPT-5 MiniLeader
SWE-bench Verified70.0%59.8%DeepSeek V3.2
SWE-bench Multilingual59.0%39.7%DeepSeek V3.2
LMArena WebDev1362Not measuredOnly DeepSeek V3.2 measured
AA Coding Index44.2Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Vals AI)80.7%86.6%GPT-5 Mini
SWE-bench Verified (Vals AI)67.6%60.8%DeepSeek V3.2
Vibe Code Bench (Vals AI)5.1%14.2%GPT-5 Mini
LiveCodeBench (Artificial Analysis run)86.2%83.8%DeepSeek V3.2
SciCodeNot measured39.0%Only GPT-5 Mini measured
Terminal-Bench Hard (Artificial Analysis run)35.6%33.3%DeepSeek V3.2
Terminal-Bench39.6%34.8%DeepSeek V3.2
WeirdMLNot measured52.7%Only GPT-5 Mini measured
LMArena Text: coding14531406DeepSeek V3.2
LMArena Text: software and IT14491394DeepSeek V3.2
LMArena WebDev: React1350Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev: HTML1371Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V3.2 and GPT-5 Mini
BenchmarkDeepSeek V3.2GPT-5 MiniLeader
AA Intelligence Index21.520.6DeepSeek V3.2
Epoch Capabilities Index146.1145.3DeepSeek V3.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for DeepSeek V3.2 and GPT-5 Mini
BenchmarkDeepSeek V3.2GPT-5 MiniLeader
τ²-Bench Telecom90.6%71.1%DeepSeek V3.2
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
Vending-Bench 2$1,034-$31DeepSeek V3.2
Berkeley Function Calling Leaderboard (BFCL)Not measured55.5%Only GPT-5 Mini measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index61
Reasoning benchmarks for DeepSeek V3.2 and GPT-5 Mini
BenchmarkDeepSeek V3.2GPT-5 MiniLeader
GPQA Diamond80.3%80.3%Tie
MMMU Pro (Vals AI)Not measured78.9%Only GPT-5 Mini measured
GPQA Diamond (Artificial Analysis run)84.0%82.8%DeepSeek V3.2
Humanity's Last Exam (Artificial Analysis run)24.6%21.5%DeepSeek V3.2
GPQA Diamond (Epoch AI run)Not measured75.0%Only GPT-5 Mini measured
ARC-AGI57.0%54.3%DeepSeek V3.2
ARC-AGI-24.0%4.4%GPT-5 Mini
Chess puzzlesNot measured24.0%Only GPT-5 Mini measured
Mystery game puzzlesNot measured10.0%Only GPT-5 Mini measured
VPCTNot measured40.2%Only GPT-5 Mini measured
LMArena Text: hard prompts14341380DeepSeek V3.2
LMArena Text: expert14361379DeepSeek V3.2
LMArena Text: hard prompts in English14461383DeepSeek V3.2
LMArena Vision: diagramsNot measured1202Only GPT-5 Mini measured
LMArena Vision: homeworkNot measured1210Only GPT-5 Mini measured
Kagi LLM BenchmarkNot measured70.3%Only GPT-5 Mini measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index42
Math benchmarks for DeepSeek V3.2 and GPT-5 Mini
BenchmarkDeepSeek V3.2GPT-5 MiniLeader
AIME84.6%91.5%GPT-5 Mini
MATH 500 (Vals AI)Not measured94.8%Only GPT-5 Mini measured
MGSM (Vals AI)86.0%92.6%GPT-5 Mini
AA Math Index92.090.7DeepSeek V3.2
AIME 2025 (Artificial Analysis run)92.0%90.7%DeepSeek V3.2
OTIS Mock AIMENot measured86.7%Only GPT-5 Mini measured
FrontierMath, tiers 1 to 3Not measured46.7%Only GPT-5 Mini measured
FrontierMath, tier 4Not measured12.2%Only GPT-5 Mini measured
ProofBenchNot measured9.0%Only GPT-5 Mini measured
MATH level 5Not measured97.8%Only GPT-5 Mini measured
LMArena Text: math14351378DeepSeek V3.2
LMArena Text: mathematical work14401380DeepSeek V3.2
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index65
Knowledge benchmarks for DeepSeek V3.2 and GPT-5 Mini
BenchmarkDeepSeek V3.2GPT-5 MiniLeader
MMLU Pro84.9%82.2%DeepSeek V3.2
LegalBench (Vals AI)76.1%81.8%GPT-5 Mini
CaseLaw (Vals AI)55.4%68.5%GPT-5 Mini
CorpFin (Vals AI)51.0%60.2%GPT-5 Mini
TaxEval (Vals AI)68.2%75.2%GPT-5 Mini
MortgageTax (Vals AI)Not measured66.9%Only GPT-5 Mini measured
MedQA (Vals AI)93.9%96.1%GPT-5 Mini
MedCode (Vals AI)Not measured43.0%Only GPT-5 Mini measured
MMLU Pro (Artificial Analysis run)86.2%83.7%DeepSeek V3.2
SimpleQA VerifiedNot measured21.6%Only GPT-5 Mini measured
LMArena Text: science14461371DeepSeek V3.2
LMArena Text: medicine and healthcare14401380DeepSeek V3.2
LMArena Text: legal and government14251375DeepSeek V3.2
LMArena Text: business and finance14101358DeepSeek V3.2
FACTS Benchmark SuiteNot measured38.6%Only GPT-5 Mini measured
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index62
Web design benchmarks for DeepSeek V3.2 and GPT-5 Mini
BenchmarkDeepSeek V3.2GPT-5 MiniLeader
Design Arena: websites11751125DeepSeek V3.2
Design Arena: UI components11461103DeepSeek V3.2
Design Arena: game dev11311129DeepSeek V3.2
Design Arena: data viz11581131DeepSeek V3.2
Design Arena: 3D11321036DeepSeek V3.2
Design Arena: all code categories11631114DeepSeek V3.2
Design Arena: SVG10321091GPT-5 Mini
Design Arena: ASCII art10831125GPT-5 Mini
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index192
General benchmarks for DeepSeek V3.2 and GPT-5 Mini
BenchmarkDeepSeek V3.2GPT-5 MiniLeader
SAGE (Vals AI)Not measured43.0%Only GPT-5 Mini measured
MedScribe (Vals AI)Not measured80.6%Only GPT-5 Mini measured
IFBench60.7%75.4%GPT-5 Mini
Long context reasoning (AA-LCR)73.3%72.3%DeepSeek V3.2
DTBench85.6%80.5%DeepSeek V3.2
LMCA28.8%34.2%GPT-5 Mini
Fiction.LiveBenchNot measured69.4%Only GPT-5 Mini measured
Creative writing (Lech Mazur)Not measured83.1%Only GPT-5 Mini measured
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251373DeepSeek V3.2
LMArena Text: instruction following14131357DeepSeek V3.2
LMArena Text: creative writing14001325DeepSeek V3.2
LMArena VisionNot measured1202Only GPT-5 Mini measured
LMArena Text: English14391379DeepSeek V3.2
LMArena Text: non-English14091363DeepSeek V3.2
LMArena Text: Chinese14551386DeepSeek V3.2
LMArena Text: German14131366DeepSeek V3.2
LMArena Text: Japanese13741341DeepSeek V3.2
LMArena Text: Korean13701308DeepSeek V3.2
LMArena Text: French14291386DeepSeek V3.2
LMArena Text: Spanish14241354DeepSeek V3.2
LMArena Text: Russian14241362DeepSeek V3.2
LMArena Text: Polish14191378DeepSeek V3.2
LMArena Text: multi-turn14271363DeepSeek V3.2
LMArena Text: longer queries14281355DeepSeek V3.2
LMArena Text: writing and language14071344DeepSeek V3.2
LMArena Text: entertainment and media13951340DeepSeek V3.2
LMArena Vision: EnglishNot measured1216Only GPT-5 Mini measured
LMArena Vision: ChineseNot measured1214Only GPT-5 Mini measured
LMArena Vision: reading textNot measured1199Only GPT-5 Mini measured
LMArena Vision: humorNot measured1205Only GPT-5 Mini measured
LMArena Vision: captioningNot measured1217Only GPT-5 Mini measured
LMArena Vision: recognizing thingsNot measured1226Only GPT-5 Mini measured
LMArena Vision: creative writingNot measured1181Only GPT-5 Mini measured
Neither model has a result on the other 11 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-5 Mini
BenchmarkDeepSeek V3.2GPT-5 MiniLeader
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-5 Mini$0.0013Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
GPT-5 Mini$0.018Fits in one request

DeepSeek V3.2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
GPT-5 Mini$0.070Fits in one request

DeepSeek V3.2 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-5 Mini
SpecificationDeepSeek V3.2OpenAI GPT-5 Mini
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedDecember 1, 2025August 7, 2025
Context window164K400K
Input $/Mtok$0.29$0.25
Output $/Mtok$0.88$2.00
Coding index30.034.2
Independent measurements behind it32
Cost per solved task$0.99$0.08
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than GPT-5 Mini for coding?

Pick GPT-5 Mini for coding: it scores 34.2 on the Vibe Coding Index against 30.0 for DeepSeek V3.2, though on 2 benchmarks against 3. Pick DeepSeek V3.2 for output tokens 2.3x cheaper ($0.88 vs $2.00 per million) and work measured by SWE-bench Verified or SWE-bench Multilingual, where it leads.

Which is cheaper, DeepSeek V3.2 or GPT-5 Mini?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and GPT-5 Mini $0.08.

Which has the bigger context window, DeepSeek V3.2 or GPT-5 Mini?

GPT-5 Mini, with 400K tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs GPT-5 Mini comparison based on?

68 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-5 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/deepseek-v3-2-vs-gpt-5-mini" title="DeepSeek V3.2 vs GPT-5 Mini, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/deepseek-v3-2-vs-gpt-5-mini">LLMBenchmark.ai, DeepSeek V3.2 vs GPT-5 Mini</a></p>