LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs GPT-4.1 Mini

Updated October 21, 2026. 61 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V3.2 Replace GPT-4.1 Mini
DeepSeek V3.2DeepSeek
Coding
54.4
Overall
21.5
Output $/M
$0.42
57
GPT-4.1 MiniOpenAI
Coding
28.5
Overall
10.2
Output $/M
$1.60
4
vs boards won of 61 shared

Decision reading

Pick DeepSeek V3.2 for coding: it scores 54.4 on the Vibe Coding Index against 28.5 for GPT-4.1 Mini.

Pick GPT-4.1 Mini when the context window is larger, 1.05M against 164K tokens, or when what matters is MGSM (Vals AI) or LegalBench (Vals AI), where it leads.

Model ADeepSeek V3.2DeepSeek54.4/1002 independent benchmarks$0.99 per solved taskModel BGPT-4.1 MiniOpenAI28.5/1002 independent benchmarks$1.818 per solved task
Shared results
61
DeepSeek V3.2 only
14
GPT-4.1 Mini only
23
Like-for-like categories
8 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
DeepSeek V3.2 54.4 from 2 benchmarks, GPT-4.1 Mini 28.5 from 2 benchmarks.
Widest category
Agentic work, 37.7 points apart on average over 1 shared benchmark.
Widest single gap
ARC-AGI: DeepSeek V3.2 57.0% against GPT-4.1 Mini 3.5%, 53.5 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.42 against GPT-4.1 Mini $1.60 per million output tokens, 3.8x apart.
Context window
DeepSeek V3.2 takes 164K tokens, GPT-4.1 Mini 1.05M.

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-4.1 MiniTies
Coding70
Intelligence20
Agentic work10
Reasoning80
Math51
Knowledge73
Web design60
General210
All shared boards574
CodingLike-for-likeFour of these boards feed the Vibe Coding Index70
Coding benchmarks for DeepSeek V3.2 and GPT-4.1 Mini
BenchmarkDeepSeek V3.2GPT-4.1 MiniLeader
Aider polyglotNot measured32.4%Only GPT-4.1 Mini measured
SWE-bench Verified70.0%23.9%DeepSeek V3.2
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev1362Not measuredOnly DeepSeek V3.2 measured
AA Coding Index44.220.2DeepSeek V3.2
LiveCodeBench (Vals AI)80.7%58.2%DeepSeek V3.2
SWE-bench Verified (Vals AI)67.6%Not measuredOnly DeepSeek V3.2 measured
Vibe Code Bench (Vals AI)5.1%Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Artificial Analysis run)86.2%48.3%DeepSeek V3.2
Terminal-Bench Hard (Artificial Analysis run)35.6%7.6%DeepSeek V3.2
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
WeirdMLNot measured37.6%Only GPT-4.1 Mini measured
LMArena Text: coding14531367DeepSeek V3.2
LMArena Text: software and IT14491360DeepSeek 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 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V3.2 and GPT-4.1 Mini
BenchmarkDeepSeek V3.2GPT-4.1 MiniLeader
AA Intelligence Index21.510.2DeepSeek V3.2
Epoch Capabilities Index146.1134.9DeepSeek V3.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.2 and GPT-4.1 Mini
BenchmarkDeepSeek V3.2GPT-4.1 MiniLeader
τ²-Bench Telecom90.6%52.9%DeepSeek V3.2
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
Vending-Bench 2$1,034Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
Reasoning benchmarks for DeepSeek V3.2 and GPT-4.1 Mini
BenchmarkDeepSeek V3.2GPT-4.1 MiniLeader
GPQA Diamond80.3%67.9%DeepSeek V3.2
MMMU Pro (Vals AI)Not measured70.5%Only GPT-4.1 Mini measured
GPQA Diamond (Artificial Analysis run)84.0%66.4%DeepSeek V3.2
Humanity's Last Exam (Artificial Analysis run)24.6%5.0%DeepSeek V3.2
GPQA Diamond (Epoch AI run)Not measured65.8%Only GPT-4.1 Mini measured
ARC-AGI57.0%3.5%DeepSeek V3.2
ARC-AGI-24.0%0.0%DeepSeek V3.2
Chess puzzlesNot measured1.0%Only GPT-4.1 Mini measured
Mystery game puzzlesNot measured7.0%Only GPT-4.1 Mini measured
LMArena Text: hard prompts14341349DeepSeek V3.2
LMArena Text: expert14361338DeepSeek V3.2
LMArena Text: hard prompts in English14461362DeepSeek V3.2
LMArena Vision: diagramsNot measured1182Only GPT-4.1 Mini measured
LMArena Vision: homeworkNot measured1214Only GPT-4.1 Mini measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index51
Math benchmarks for DeepSeek V3.2 and GPT-4.1 Mini
BenchmarkDeepSeek V3.2GPT-4.1 MiniLeader
AIME84.6%49.4%DeepSeek V3.2
MATH 500 (Vals AI)Not measured88.0%Only GPT-4.1 Mini measured
MGSM (Vals AI)86.0%87.8%GPT-4.1 Mini
AA Math Index92.046.3DeepSeek V3.2
AIME 2025 (Artificial Analysis run)92.0%46.3%DeepSeek V3.2
OTIS Mock AIMENot measured44.7%Only GPT-4.1 Mini measured
FrontierMath, tiers 1 to 3Not measured6.7%Only GPT-4.1 Mini measured
MATH level 5Not measured87.3%Only GPT-4.1 Mini measured
LMArena Text: math14351343DeepSeek V3.2
LMArena Text: mathematical work14401347DeepSeek V3.2
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index73
Knowledge benchmarks for DeepSeek V3.2 and GPT-4.1 Mini
BenchmarkDeepSeek V3.2GPT-4.1 MiniLeader
MMLU Pro84.9%77.2%DeepSeek V3.2
LegalBench (Vals AI)76.1%78.0%GPT-4.1 Mini
CaseLaw (Vals AI)55.4%Not measuredOnly DeepSeek V3.2 measured
CorpFin (Vals AI)51.0%57.9%GPT-4.1 Mini
TaxEval (Vals AI)68.2%71.9%GPT-4.1 Mini
MortgageTax (Vals AI)Not measured65.5%Only GPT-4.1 Mini measured
MedQA (Vals AI)93.9%84.6%DeepSeek V3.2
MMLU Pro (Artificial Analysis run)86.2%78.1%DeepSeek V3.2
SimpleQA VerifiedNot measured12.7%Only GPT-4.1 Mini measured
LMArena Text: science14461328DeepSeek V3.2
LMArena Text: medicine and healthcare14401324DeepSeek V3.2
LMArena Text: legal and government14251343DeepSeek V3.2
LMArena Text: business and finance14101322DeepSeek V3.2
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for DeepSeek V3.2 and GPT-4.1 Mini
BenchmarkDeepSeek V3.2GPT-4.1 MiniLeader
Design Arena: websites1175997DeepSeek V3.2
Design Arena: UI components1149961DeepSeek V3.2
Design Arena: game dev11321071DeepSeek V3.2
Design Arena: data viz11581034DeepSeek V3.2
Design Arena: 3D1133837DeepSeek V3.2
Design Arena: all code categories1164994DeepSeek V3.2
Design Arena: SVG1032Not measuredOnly DeepSeek V3.2 measured
Design Arena: ASCII art1082Not 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 index210
General benchmarks for DeepSeek V3.2 and GPT-4.1 Mini
BenchmarkDeepSeek V3.2GPT-4.1 MiniLeader
IFBench60.7%38.3%DeepSeek V3.2
Long context reasoning (AA-LCR)73.3%44.0%DeepSeek V3.2
DTBench85.6%68.8%DeepSeek V3.2
LMCA28.8%21.1%DeepSeek V3.2
Fiction.LiveBenchNot measured44.4%Only GPT-4.1 Mini measured
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251341DeepSeek V3.2
LMArena Text: instruction following14131333DeepSeek V3.2
LMArena Text: creative writing14001299DeepSeek V3.2
LMArena VisionNot measured1181Only GPT-4.1 Mini measured
LMArena Text: English14391356DeepSeek V3.2
LMArena Text: non-English14091318DeepSeek V3.2
LMArena Text: Chinese14551329DeepSeek V3.2
LMArena Text: German14131350DeepSeek V3.2
LMArena Text: Japanese13741290DeepSeek V3.2
LMArena Text: Korean13701298DeepSeek V3.2
LMArena Text: French14291358DeepSeek V3.2
LMArena Text: Spanish14241319DeepSeek V3.2
LMArena Text: Russian14241324DeepSeek V3.2
LMArena Text: Polish14191326DeepSeek V3.2
LMArena Text: multi-turn14271354DeepSeek V3.2
LMArena Text: longer queries14281344DeepSeek V3.2
LMArena Text: writing and language14071319DeepSeek V3.2
LMArena Text: entertainment and media13951300DeepSeek V3.2
LMArena Vision: EnglishNot measured1191Only GPT-4.1 Mini measured
LMArena Vision: ChineseNot measured1186Only GPT-4.1 Mini measured
LMArena Vision: reading textNot measured1188Only GPT-4.1 Mini measured
LMArena Vision: humorNot measured1182Only GPT-4.1 Mini measured
LMArena Vision: captioningNot measured1174Only GPT-4.1 Mini measured
LMArena Vision: recognizing thingsNot measured1187Only GPT-4.1 Mini measured
LMArena Vision: creative writingNot measured1182Only GPT-4.1 Mini measured
Neither model has a result on the other 14 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-4.1 Mini
BenchmarkDeepSeek V3.2GPT-4.1 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$0.0005Fits in one request
GPT-4.1 Mini$0.0012Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.015Fits in one request
GPT-4.1 Mini$0.025Fits in one request

DeepSeek V3.2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.060Exceeds the context window
GPT-4.1 Mini$0.096Fits 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-4.1 Mini
SpecificationDeepSeek V3.2OpenAI GPT-4.1 Mini
MakerDeepSeekOpenAI
WeightsOpen weightsNo public weights listed
ReleasedDecember 1, 2025April 14, 2025
Context window164K1.05M
Input $/Mtok$0.28$0.40
Output $/Mtok$0.42$1.60
Coding index54.428.5
Independent measurements behind it22
Cost per solved task$0.99$1.818
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than GPT-4.1 Mini for coding?

Pick DeepSeek V3.2 for coding: it scores 54.4 on the Vibe Coding Index against 28.5 for GPT-4.1 Mini. Pick GPT-4.1 Mini when the context window is larger, 1.05M against 164K tokens, or when what matters is MGSM (Vals AI) or LegalBench (Vals AI), where it leads.

Which is cheaper, DeepSeek V3.2 or GPT-4.1 Mini?

DeepSeek V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens; GPT-4.1 Mini costs $0.40 and $1.60. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and GPT-4.1 Mini $1.818.

Which has the bigger context window, DeepSeek V3.2 or GPT-4.1 Mini?

GPT-4.1 Mini, with 1.05M tokens against 164K.

How many benchmarks is the DeepSeek V3.2 vs GPT-4.1 Mini comparison based on?

61 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 2 independent benchmarks and GPT-4.1 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-4-1-mini" title="DeepSeek V3.2 vs GPT-4.1 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-4-1-mini">LLMBenchmark.ai, DeepSeek V3.2 vs GPT-4.1 Mini</a></p>