Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs MiniMax M2.7

DeepSeek V4 Pro 0423 leads MiniMax M2.7 on coding, 38.7 to 36.2 on the Vibe Coding Index, and MiniMax M2.7 costs 2.3x less per output token ($1.20 vs $2.716 per million). Updated October 22, 2026; 64 benchmarks have a result for both.

Replace DeepSeek V4 Pro 0423 Replace MiniMax M2.7
DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
50.0
Output $/M
$2.716
58
MiniMax M2.7MiniMax
Coding
36.2
Overall
44.5
Output $/M
$1.20
5
vs boards won of 64 shared, 1 tied

DeepSeek V4 Pro 0423 or MiniMax M2.7: which to pick

Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 36.2 for MiniMax M2.7.

Pick MiniMax M2.7 for output tokens 2.3x cheaper ($1.20 vs $2.716 per million) and work measured by LegalBench (Vals AI) or CaseLaw (Vals AI), where it leads.

Model ADeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved taskModel BMiniMax M2.7MiniMax36.2/1003 independent benchmarks$0.64 per solved task
Shared results
64
DeepSeek V4 Pro 0423 only
20
MiniMax M2.7 only
10
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 V4 Pro 0423 38.7 from 5 benchmarks, MiniMax M2.7 36.2 from 3 benchmarks.
Widest category
Agentic work, 16.2 points apart on average over 5 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): DeepSeek V4 Pro 0423 49.9% against MiniMax M2.7 11.9%, 38.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $2.716 against MiniMax M2.7 $1.20 per million output tokens, 2.3x apart.
Context window
DeepSeek V4 Pro 0423 takes 1.05M 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 V4 Pro 0423BarsMiniMax M2.7Ties
Coding1301 tie
Intelligence20
Agentic work50
Reasoning40
Math30
Knowledge82
Web design62
General171
All shared boards5851 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index130
Coding benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.7
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.7Leader
LMArena WebDev14471399DeepSeek V4 Pro 0423
AA Coding Index59.452.6DeepSeek V4 Pro 0423
LiveCodeBench (Vals AI)87.5%79.9%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)77.4%73.8%DeepSeek V4 Pro 0423
Terminal-Bench 4 (Vals AI)11.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Vibe Code Bench (Vals AI)49.9%11.9%DeepSeek V4 Pro 0423
Code migration (Vals AI)26.2%8.7%DeepSeek V4 Pro 0423
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)50.2%48.7%DeepSeek V4 Pro 0423
SkillsBench (Vals AI)51.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
SciCodeNot measured50.1%Only MiniMax M2.7 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured39.4%Only MiniMax M2.7 measured
Terminal-BenchNot measured45.1%Only MiniMax M2.7 measured
FrontierCode17.6%Not measuredOnly DeepSeek V4 Pro 0423 measured
WeirdML48.9%37.0%DeepSeek V4 Pro 0423
ALE-Bench1006.1599.3DeepSeek V4 Pro 0423
LMArena Text: coding14701454DeepSeek V4 Pro 0423
LMArena Text: software and IT14691446DeepSeek V4 Pro 0423
LMArena WebDev: React14411388DeepSeek V4 Pro 0423
LMArena WebDev: HTML14351401DeepSeek V4 Pro 0423
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.7
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.7Leader
AA Intelligence Index30.422.8DeepSeek V4 Pro 0423
Epoch Capabilities Index149.1145.8DeepSeek V4 Pro 0423
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
Agentic work benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.7
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.7Leader
AA Agentic Index26.315.3DeepSeek V4 Pro 0423
Design Arena: agents building web apps1000Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: agents building full-stack apps948Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: agents building Godot games1059Not measuredOnly DeepSeek V4 Pro 0423 measured
Finance Agent (Vals AI)44.1%27.9%DeepSeek V4 Pro 0423
Tax Agent Bench (Vals AI)25.2%6.9%DeepSeek V4 Pro 0423
Legal Research Bench (Vals AI)23.1%10.6%DeepSeek V4 Pro 0423
Excel Modeling Benchmark (Vals AI)51.6%28.4%DeepSeek V4 Pro 0423
τ²-Bench TelecomNot measured84.8%Only MiniMax M2.7 measured
Vending-Bench 2$3,285Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 31 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
Reasoning benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.7
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.7Leader
GPQA Diamond89.4%86.6%DeepSeek V4 Pro 0423
GPQA Diamond (Artificial Analysis run)Not measured87.4%Only MiniMax M2.7 measured
Humanity's Last Exam (Artificial Analysis run)Not measured29.6%Only MiniMax M2.7 measured
GPQA Diamond (Epoch AI run)90.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
Chess puzzles19.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
Mystery game puzzles17.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: hard prompts14611422DeepSeek V4 Pro 0423
LMArena Text: expert14631443DeepSeek V4 Pro 0423
LMArena Text: hard prompts in English14661441DeepSeek V4 Pro 0423
Kagi LLM Benchmark53.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.7
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.7Leader
AIMENot measured91.0%Only MiniMax M2.7 measured
OTIS Mock AIME96.7%Not measuredOnly DeepSeek V4 Pro 0423 measured
FrontierMath, tiers 1 to 345.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
FrontierMath, tier 42.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
ProofBench16.0%3.0%DeepSeek V4 Pro 0423
LMArena Text: math14431421DeepSeek V4 Pro 0423
LMArena Text: mathematical work14551437DeepSeek V4 Pro 0423
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
Knowledge benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.7
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.7Leader
MMLU Pro87.3%80.4%DeepSeek V4 Pro 0423
LegalBench (Vals AI)80.3%84.0%MiniMax M2.7
CaseLaw (Vals AI)59.4%60.9%MiniMax M2.7
CorpFin (Vals AI)61.4%61.2%DeepSeek V4 Pro 0423
TaxEval (Vals AI)72.1%66.6%DeepSeek V4 Pro 0423
MedCode (Vals AI)40.5%34.4%DeepSeek V4 Pro 0423
SimpleQA Verified47.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: science14701416DeepSeek V4 Pro 0423
LMArena Text: medicine and healthcare14661409DeepSeek V4 Pro 0423
LMArena Text: legal and government14641403DeepSeek V4 Pro 0423
LMArena Text: business and finance14431407DeepSeek V4 Pro 0423
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index62
Web design benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.7
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.7Leader
Design Arena: websites12341242MiniMax M2.7
Design Arena: UI components12191207DeepSeek V4 Pro 0423
Design Arena: game dev12281209DeepSeek V4 Pro 0423
Design Arena: data viz12031233MiniMax M2.7
Design Arena: 3D12531194DeepSeek V4 Pro 0423
Design Arena: all code categories12401233DeepSeek V4 Pro 0423
Design Arena: SVG11391137DeepSeek V4 Pro 0423
Design Arena: ASCII art11491136DeepSeek V4 Pro 0423
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index171
General benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.7
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.7Leader
Public Benefits Bench (Vals AI)62.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
MedScribe (Vals AI)75.1%79.9%MiniMax M2.7
IFBenchNot measured75.7%Only MiniMax M2.7 measured
Long context reasoning (AA-LCR)Not measured78.3%Only MiniMax M2.7 measured
DTBench90.7%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMCA41.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
Surface Evolver Bench40.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
ExploitBenchNot measured13.3%Only MiniMax M2.7 measured
CL-bench Life13.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text14511405DeepSeek V4 Pro 0423
LMArena Text: instruction following14451405DeepSeek V4 Pro 0423
LMArena Text: creative writing14461354DeepSeek V4 Pro 0423
LMArena Text: English14591426DeepSeek V4 Pro 0423
LMArena Text: non-English14391382DeepSeek V4 Pro 0423
LMArena Text: Chinese14811442DeepSeek V4 Pro 0423
LMArena Text: German14581398DeepSeek V4 Pro 0423
LMArena Text: Japanese14461260DeepSeek V4 Pro 0423
LMArena Text: Korean14091314DeepSeek V4 Pro 0423
LMArena Text: French14731424DeepSeek V4 Pro 0423
LMArena Text: Spanish14571402DeepSeek V4 Pro 0423
LMArena Text: Russian14531383DeepSeek V4 Pro 0423
LMArena Text: Polish14611387DeepSeek V4 Pro 0423
LMArena Text: multi-turn14681412DeepSeek V4 Pro 0423
LMArena Text: longer queries14581418DeepSeek V4 Pro 0423
LMArena Text: writing and language14471376DeepSeek V4 Pro 0423
LMArena Text: entertainment and media14311360DeepSeek V4 Pro 0423
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 V4 Pro 0423 and MiniMax M2.7
BenchmarkDeepSeek V4 Pro 0423MiniMax 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 V4 Pro 0423$0.0026Fits in one request
MiniMax M2.7$0.0009Fits in one request

MiniMax M2.7 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0423$0.069Fits in one request
MiniMax M2.7$0.019Fits in one request

MiniMax M2.7 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.272Fits in one request
MiniMax M2.7$0.072Exceeds the context window

MiniMax M2.7 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 V4 Pro 0423 and MiniMax M2.7
SpecificationDeepSeek V4 Pro 0423MiniMax M2.7
MakerDeepSeekMiniMax
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026March 18, 2026
Context window1.05M205K
Input $/Mtok$1.225$0.30
Output $/Mtok$2.716$1.20
Coding index38.736.2
Independent measurements behind it53
Cost per solved task$0.57$0.64
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0423 better than MiniMax M2.7 for coding?

Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 36.2 for MiniMax M2.7. Pick MiniMax M2.7 for output tokens 2.3x cheaper ($1.20 vs $2.716 per million) and work measured by LegalBench (Vals AI) or CaseLaw (Vals AI), where it leads.

Which is cheaper, DeepSeek V4 Pro 0423 or MiniMax M2.7?

DeepSeek V4 Pro 0423 costs $1.225 per million input tokens and $2.716 per million output tokens; MiniMax M2.7 costs $0.30 and $1.20. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and MiniMax M2.7 $0.64.

Which has the bigger context window, DeepSeek V4 Pro 0423 or MiniMax M2.7?

DeepSeek V4 Pro 0423, with 1.05M tokens against 205K.

How many benchmarks is the DeepSeek V4 Pro 0423 vs MiniMax M2.7 comparison based on?

64 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 independent benchmarks and MiniMax M2.7's on 3. 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-v4-pro-vs-minimax-minimax-m2-7" title="DeepSeek V4 Pro 0423 vs MiniMax M2.7, 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-v4-pro-vs-minimax-minimax-m2-7">LLMBenchmark.ai, DeepSeek V4 Pro 0423 vs MiniMax M2.7</a></p>