LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs MiniMax M2.5

Updated October 21, 2026. 53 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V4 Pro 0423 Replace MiniMax M2.5
DeepSeek V4 Pro 0423DeepSeek
Coding
35.3
Overall
30.4
Output $/M
$1.9105
52
MiniMax M2.5MiniMax
Coding
59.4
Overall
22.8
Output $/M
$0.95
1
vs boards won of 53 shared

Decision reading

Pick MiniMax M2.5 for coding: it scores 59.4 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423.

Pick DeepSeek V4 Pro 0423 when a solved task costs $0.57 against $0.62, or when the context window is larger, 1.05M against 205K tokens.

Model ADeepSeek V4 Pro 0423DeepSeek35.3/1001 independent benchmark$0.57 per solved taskModel BMiniMax M2.5MiniMax59.4/1002 independent benchmarks$0.62 per solved task
Shared results
53
DeepSeek V4 Pro 0423 only
30
MiniMax M2.5 only
14
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 V4 Pro 0423 35.3 from 1 benchmark, MiniMax M2.5 59.4 from 2 benchmarks.
Widest category
Agentic work, 20.5 points apart on average over 1 shared benchmark.
Widest single gap
LMArena Text: Japanese: DeepSeek V4 Pro 0423 1446 against MiniMax M2.5 1171, 45.9 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $1.9105 against MiniMax M2.5 $0.95 per million output tokens, 2.0x apart.
Context window
DeepSeek V4 Pro 0423 takes 1.05M tokens, MiniMax M2.5 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 M2.5Ties
Coding90
Intelligence20
Agentic work10
Reasoning40
Math30
Knowledge90
Web design61
General180
All shared boards521
CodingLike-for-likeFour of these boards feed the Vibe Coding Index90
Coding benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.5
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.5Leader
SWE-bench VerifiedNot measured75.8%Only MiniMax M2.5 measured
SWE-bench MultilingualNot measured68.3%Only MiniMax M2.5 measured
LMArena WebDev14471386DeepSeek V4 Pro 0423
AA Coding Index59.4Not measuredOnly DeepSeek V4 Pro 0423 measured
LiveCodeBench (Vals AI)87.5%79.2%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)77.4%74.2%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%14.8%DeepSeek V4 Pro 0423
Code migration (Vals AI)26.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
ProgramBench (Vals AI)0.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
Terminal-Bench 2.1 (Vals AI)50.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
SkillsBench (Vals AI)51.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured34.8%Only MiniMax M2.5 measured
Terminal-BenchNot measured42.7%Only MiniMax M2.5 measured
FrontierCode17.6%Not measuredOnly DeepSeek V4 Pro 0423 measured
WeirdML48.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
ALE-Bench1006.1618.2DeepSeek V4 Pro 0423
LMArena Text: coding14701380DeepSeek V4 Pro 0423
LMArena Text: software and IT14691383DeepSeek V4 Pro 0423
LMArena WebDev: React14411374DeepSeek V4 Pro 0423
LMArena WebDev: HTML14351414DeepSeek V4 Pro 0423
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.5
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.5Leader
AA Intelligence Index30.422.8DeepSeek V4 Pro 0423
Epoch Capabilities Index149.1146.6DeepSeek V4 Pro 0423
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.5
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.5Leader
AA Agentic Index26.3Not measuredOnly DeepSeek V4 Pro 0423 measured
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%Not measuredOnly DeepSeek V4 Pro 0423 measured
Tax Agent Bench (Vals AI)25.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
Legal Research Bench (Vals AI)23.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Excel Modeling Benchmark (Vals AI)51.6%Not measuredOnly DeepSeek V4 Pro 0423 measured
τ²-Bench TelecomNot measured95.3%Only MiniMax M2.5 measured
Vending-Bench 2$3,285-$23DeepSeek V4 Pro 0423
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
Reasoning benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.5
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.5Leader
GPQA Diamond89.4%82.1%DeepSeek V4 Pro 0423
GPQA Diamond (Artificial Analysis run)Not measured84.8%Only MiniMax M2.5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured20.5%Only MiniMax M2.5 measured
GPQA Diamond (Epoch AI run)90.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
ARC-AGINot measured63.7%Only MiniMax M2.5 measured
ARC-AGI-2Not measured4.9%Only MiniMax M2.5 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 prompts14611372DeepSeek V4 Pro 0423
LMArena Text: expert14631378DeepSeek V4 Pro 0423
LMArena Text: hard prompts in English14661384DeepSeek V4 Pro 0423
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.5
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.5Leader
AIMENot measured88.8%Only MiniMax M2.5 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%4.0%DeepSeek V4 Pro 0423
LMArena Text: math14431378DeepSeek V4 Pro 0423
LMArena Text: mathematical work14551378DeepSeek 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 index90
Knowledge benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.5
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.5Leader
MMLU Pro87.3%80.1%DeepSeek V4 Pro 0423
LegalBench (Vals AI)80.3%80.0%DeepSeek V4 Pro 0423
CaseLaw (Vals AI)59.4%53.5%DeepSeek V4 Pro 0423
CorpFin (Vals AI)61.4%59.6%DeepSeek V4 Pro 0423
TaxEval (Vals AI)72.1%68.2%DeepSeek V4 Pro 0423
MedQA (Vals AI)Not measured92.5%Only MiniMax M2.5 measured
MedCode (Vals AI)40.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
SimpleQA Verified47.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: science14701369DeepSeek V4 Pro 0423
LMArena Text: medicine and healthcare14661357DeepSeek V4 Pro 0423
LMArena Text: legal and government14641366DeepSeek V4 Pro 0423
LMArena Text: business and finance14431356DeepSeek V4 Pro 0423
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index61
Web design benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.5
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.5Leader
Design Arena: websites12351222DeepSeek V4 Pro 0423
Design Arena: UI components12211172DeepSeek V4 Pro 0423
Design Arena: game dev12291176DeepSeek V4 Pro 0423
Design Arena: data viz12031171DeepSeek V4 Pro 0423
Design Arena: 3D12541170DeepSeek V4 Pro 0423
Design Arena: all code categories12401207DeepSeek V4 Pro 0423
Design Arena: SVG11391147MiniMax M2.5
Design Arena: ASCII art1148Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index180
General benchmarks for DeepSeek V4 Pro 0423 and MiniMax M2.5
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.5Leader
Public Benefits Bench (Vals AI)62.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
MedScribe (Vals AI)75.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
IFBenchNot measured71.6%Only MiniMax M2.5 measured
Long context reasoning (AA-LCR)Not measured73.3%Only MiniMax M2.5 measured
DTBench90.7%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMCA41.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
CL-benchNot measured11.4%Only MiniMax M2.5 measured
Surface Evolver Bench40.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
CL-bench Life13.5%6.3%DeepSeek V4 Pro 0423
LMArena Text14511359DeepSeek V4 Pro 0423
LMArena Text: instruction following14451353DeepSeek V4 Pro 0423
LMArena Text: creative writing14461331DeepSeek V4 Pro 0423
LMArena Text: English14591380DeepSeek V4 Pro 0423
LMArena Text: non-English14391338DeepSeek V4 Pro 0423
LMArena Text: Chinese14811393DeepSeek V4 Pro 0423
LMArena Text: German14581361DeepSeek V4 Pro 0423
LMArena Text: Japanese14461171DeepSeek V4 Pro 0423
LMArena Text: Korean14091233DeepSeek V4 Pro 0423
LMArena Text: French14731363DeepSeek V4 Pro 0423
LMArena Text: Spanish14571353DeepSeek V4 Pro 0423
LMArena Text: Russian14531359DeepSeek V4 Pro 0423
LMArena Text: Polish14611334DeepSeek V4 Pro 0423
LMArena Text: multi-turn14681364DeepSeek V4 Pro 0423
LMArena Text: longer queries14581366DeepSeek V4 Pro 0423
LMArena Text: writing and language14471345DeepSeek V4 Pro 0423
LMArena Text: entertainment and media14311329DeepSeek 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 M2.5
BenchmarkDeepSeek V4 Pro 0423MiniMax M2.5Leader
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$0.0019Fits in one request
MiniMax M2.5$0.0007Fits in one request

MiniMax M2.5 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0423$0.053Fits in one request
MiniMax M2.5$0.016Fits in one request

MiniMax M2.5 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.210Fits in one request
MiniMax M2.5$0.064Exceeds the context window

MiniMax M2.5 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 M2.5
SpecificationDeepSeek V4 Pro 0423MiniMax M2.5
MakerDeepSeekMiniMax
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026February 12, 2026
Context window1.05M205K
Input $/Mtok$0.9553$0.27
Output $/Mtok$1.9105$0.95
Coding index35.359.4
Independent measurements behind it12
Cost per solved task$0.57$0.62
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0423 better than MiniMax M2.5 for coding?

Pick MiniMax M2.5 for coding: it scores 59.4 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 when a solved task costs $0.57 against $0.62, or when the context window is larger, 1.05M against 205K tokens.

Which is cheaper, DeepSeek V4 Pro 0423 or MiniMax M2.5?

DeepSeek V4 Pro 0423 costs $0.9553 per million input tokens and $1.9105 per million output tokens; MiniMax M2.5 costs $0.27 and $0.95. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and MiniMax M2.5 $0.62.

Which has the bigger context window, DeepSeek V4 Pro 0423 or MiniMax M2.5?

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

How many benchmarks is the DeepSeek V4 Pro 0423 vs MiniMax M2.5 comparison based on?

53 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0423's coding index rests on 1 independent benchmark and MiniMax M2.5's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next