LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 Exp vs MiniMax M2.7

Updated October 21, 2026. 46 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 Exp Replace MiniMax M2.7
DeepSeek V3.2 ExpDeepSeek
Coding
55.0
Overall
16.6
Output $/M
$0.41
23
MiniMax M2.7MiniMax
Coding
28.4
Overall
22.8
Output $/M
$1.20
23
vs boards won of 46 shared

Decision reading

Pick DeepSeek V3.2 Exp for coding: it scores 55.0 on the Vibe Coding Index against 28.4 for MiniMax M2.7.

Pick MiniMax M2.7 when the context window is larger, 205K against 164K tokens, or when what matters is LMArena WebDev or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model ADeepSeek V3.2 ExpDeepSeek55.0/1002 independent benchmarksNo cost per solved taskModel BMiniMax M2.7MiniMax28.4/1001 independent benchmark$0.64 per solved task
Shared results
46
DeepSeek V3.2 Exp only
11
MiniMax M2.7 only
28
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 Exp 55.0 from 2 benchmarks, MiniMax M2.7 28.4 from 1 benchmark.
Widest category
Agentic work, 50.9 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: DeepSeek V3.2 Exp 33.9% against MiniMax M2.7 84.8%, 50.9 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 Exp $0.41 against MiniMax M2.7 $1.20 per million output tokens, 2.9x apart.
Context window
DeepSeek V3.2 Exp takes 164K tokens, MiniMax M2.7 205K.

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 ExpBarsMiniMax M2.7Ties
Coding15
Intelligence02
Agentic work01
Reasoning23
Math11
Knowledge40
Web design07
General154
All shared boards2323
CodingLike-for-likeFour of these boards feed the Vibe Coding Index15
Coding benchmarks for DeepSeek V3.2 Exp and MiniMax M2.7
BenchmarkDeepSeek V3.2 ExpMiniMax M2.7Leader
Aider polyglot74.2%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena WebDev12721399MiniMax M2.7
AA Coding IndexNot measured52.6Only MiniMax M2.7 measured
LiveCodeBench (Vals AI)Not measured79.9%Only MiniMax M2.7 measured
SWE-bench Verified (Vals AI)Not measured73.8%Only MiniMax M2.7 measured
Vibe Code Bench (Vals AI)Not measured11.9%Only MiniMax M2.7 measured
Code migration (Vals AI)Not measured8.7%Only MiniMax M2.7 measured
ProgramBench (Vals AI)Not measured0.0%Only MiniMax M2.7 measured
Terminal-Bench 2.1 (Vals AI)Not measured48.7%Only MiniMax M2.7 measured
LiveCodeBench (Artificial Analysis run)78.9%Not measuredOnly DeepSeek V3.2 Exp measured
SciCodeNot measured50.1%Only MiniMax M2.7 measured
Terminal-Bench Hard (Artificial Analysis run)31.1%39.4%MiniMax M2.7
Terminal-BenchNot measured45.1%Only MiniMax M2.7 measured
WeirdML39.5%37.0%DeepSeek V3.2 Exp
ALE-BenchNot measured599.3Only MiniMax M2.7 measured
LMArena Text: coding14381454MiniMax M2.7
LMArena Text: software and IT14381446MiniMax M2.7
LMArena WebDev: ReactNot measured1388Only MiniMax M2.7 measured
LMArena WebDev: HTML12811401MiniMax M2.7
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V3.2 Exp and MiniMax M2.7
BenchmarkDeepSeek V3.2 ExpMiniMax M2.7Leader
AA Intelligence Index16.622.8MiniMax M2.7
Epoch Capabilities Index144.9145.8MiniMax M2.7
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3.2 Exp and MiniMax M2.7
BenchmarkDeepSeek V3.2 ExpMiniMax M2.7Leader
AA Agentic IndexNot measured15.3Only MiniMax M2.7 measured
Finance Agent (Vals AI)Not measured27.9%Only MiniMax M2.7 measured
Tax Agent Bench (Vals AI)Not measured6.9%Only MiniMax M2.7 measured
Legal Research Bench (Vals AI)Not measured10.6%Only MiniMax M2.7 measured
Excel Modeling Benchmark (Vals AI)Not measured28.4%Only MiniMax M2.7 measured
τ²-Bench Telecom33.9%84.8%MiniMax M2.7
TheAgentCompany42.9%Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index23
Reasoning benchmarks for DeepSeek V3.2 Exp and MiniMax M2.7
BenchmarkDeepSeek V3.2 ExpMiniMax M2.7Leader
GPQA DiamondNot measured86.6%Only MiniMax M2.7 measured
GPQA Diamond (Artificial Analysis run)79.7%87.4%MiniMax M2.7
Humanity's Last Exam (Artificial Analysis run)14.9%29.6%MiniMax M2.7
LMArena Text: hard prompts14291422DeepSeek V3.2 Exp
LMArena Text: expert14221443MiniMax M2.7
LMArena Text: hard prompts in English14441441DeepSeek V3.2 Exp
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index11
Math benchmarks for DeepSeek V3.2 Exp and MiniMax M2.7
BenchmarkDeepSeek V3.2 ExpMiniMax M2.7Leader
AIMENot measured91.0%Only MiniMax M2.7 measured
AA Math Index87.7Not measuredOnly DeepSeek V3.2 Exp measured
AIME 2025 (Artificial Analysis run)87.7%Not measuredOnly DeepSeek V3.2 Exp measured
ProofBenchNot measured3.0%Only MiniMax M2.7 measured
LMArena Text: math14221421DeepSeek V3.2 Exp
LMArena Text: mathematical work14331437MiniMax M2.7
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for DeepSeek V3.2 Exp and MiniMax M2.7
BenchmarkDeepSeek V3.2 ExpMiniMax M2.7Leader
MMLU ProNot measured80.4%Only MiniMax M2.7 measured
LegalBench (Vals AI)Not measured84.0%Only MiniMax M2.7 measured
CaseLaw (Vals AI)Not measured60.9%Only MiniMax M2.7 measured
CorpFin (Vals AI)Not measured61.2%Only MiniMax M2.7 measured
TaxEval (Vals AI)Not measured66.6%Only MiniMax M2.7 measured
MedCode (Vals AI)Not measured34.4%Only MiniMax M2.7 measured
MMLU Pro (Artificial Analysis run)85.0%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text: science14431416DeepSeek V3.2 Exp
LMArena Text: medicine and healthcare14681409DeepSeek V3.2 Exp
LMArena Text: legal and government14191403DeepSeek V3.2 Exp
LMArena Text: business and finance14121407DeepSeek V3.2 Exp
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for DeepSeek V3.2 Exp and MiniMax M2.7
BenchmarkDeepSeek V3.2 ExpMiniMax M2.7Leader
Design Arena: websites11791243MiniMax M2.7
Design Arena: UI components11661210MiniMax M2.7
Design Arena: game dev11451210MiniMax M2.7
Design Arena: data viz11521233MiniMax M2.7
Design Arena: 3D11481195MiniMax M2.7
Design Arena: all code categories11711233MiniMax M2.7
Design Arena: SVG10311136MiniMax M2.7
Design Arena: ASCII artNot measured1136Only MiniMax M2.7 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index154
General benchmarks for DeepSeek V3.2 Exp and MiniMax M2.7
BenchmarkDeepSeek V3.2 ExpMiniMax M2.7Leader
MedScribe (Vals AI)Not measured79.9%Only MiniMax M2.7 measured
IFBench54.1%75.7%MiniMax M2.7
Long context reasoning (AA-LCR)72.3%78.3%MiniMax M2.7
DTBench87.7%Not measuredOnly DeepSeek V3.2 Exp measured
LMCA29.1%Not measuredOnly DeepSeek V3.2 Exp measured
Fiction.LiveBench83.3%Not measuredOnly DeepSeek V3.2 Exp measured
CL-bench13.2%Not measuredOnly DeepSeek V3.2 Exp measured
ExploitBenchNot measured13.3%Only MiniMax M2.7 measured
CL-bench Life9.5%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena Text14251405DeepSeek V3.2 Exp
LMArena Text: instruction following14011405MiniMax M2.7
LMArena Text: creative writing14041354DeepSeek V3.2 Exp
LMArena Text: English14411426DeepSeek V3.2 Exp
LMArena Text: non-English14041382DeepSeek V3.2 Exp
LMArena Text: Chinese14611442DeepSeek V3.2 Exp
LMArena Text: German14401398DeepSeek V3.2 Exp
LMArena Text: Japanese13311260DeepSeek V3.2 Exp
LMArena Text: Korean13721314DeepSeek V3.2 Exp
LMArena Text: French14341424DeepSeek V3.2 Exp
LMArena Text: Spanish14411402DeepSeek V3.2 Exp
LMArena Text: Russian14121383DeepSeek V3.2 Exp
LMArena Text: Polish14351387DeepSeek V3.2 Exp
LMArena Text: multi-turn14221412DeepSeek V3.2 Exp
LMArena Text: longer queries14181418MiniMax M2.7
LMArena Text: writing and language14071376DeepSeek V3.2 Exp
LMArena Text: entertainment and media14071360DeepSeek V3.2 Exp
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 Exp and MiniMax M2.7
BenchmarkDeepSeek V3.2 ExpMiniMax M2.7Leader
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
MiniMax M2.7$0.0009Fits in one request

DeepSeek V3.2 Exp costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2 Exp$0.015Fits in one request
MiniMax M2.7$0.019Fits in one request

DeepSeek V3.2 Exp costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2 Exp$0.058Exceeds the context window
MiniMax M2.7$0.072Exceeds the context window

DeepSeek V3.2 Exp 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 MiniMax M2.7
SpecificationDeepSeek V3.2 ExpMiniMax M2.7
MakerDeepSeekMiniMax
WeightsOpen weightsOpen weights
ReleasedSeptember 29, 2025March 18, 2026
Context window164K205K
Input $/Mtok$0.27$0.30
Output $/Mtok$0.41$1.20
Coding index55.028.4
Independent measurements behind it21
Cost per solved taskNot computable$0.64
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 Exp better than MiniMax M2.7 for coding?

Pick DeepSeek V3.2 Exp for coding: it scores 55.0 on the Vibe Coding Index against 28.4 for MiniMax M2.7. Pick MiniMax M2.7 when the context window is larger, 205K against 164K tokens, or when what matters is LMArena WebDev or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, DeepSeek V3.2 Exp or MiniMax M2.7?

DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens; MiniMax M2.7 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M2.7 only.

Which has the bigger context window, DeepSeek V3.2 Exp or MiniMax M2.7?

MiniMax M2.7, with 205K tokens against 164K.

How many benchmarks is the DeepSeek V3.2 Exp vs MiniMax M2.7 comparison based on?

46 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2 Exp's coding index rests on 2 independent benchmarks and MiniMax M2.7's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next