Enter opens the highlighted result. Esc closes.

MiniMax M2.5 vs o3 Mini

MiniMax M2.5 leads o3 Mini on the Artificial Analysis Intelligence Index, 22.8 to 12.5, and MiniMax M2.5 costs 3.7x less per output token ($1.20 vs $4.40 per million). Updated October 22, 2026; 47 benchmarks have a result for both.

Replace MiniMax M2.5 Replace o3 Mini
MiniMax M2.5MiniMax
Coding
37.2
Overall
37.3
Output $/M
$1.20
41
o3 MiniOpenAI
Coding
No data
Overall
38.0
Output $/M
$4.40
6
vs boards won of 47 shared

MiniMax M2.5 or o3 Mini: which to pick

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; o3 Mini has none, so the two cannot be ranked on coding.

Pick o3 Mini for work measured by LMArena Text: math or LMArena Text: mathematical work, where it leads.

Model AMiniMax M2.5MiniMax37.2/1003 independent benchmarks$0.62 per solved taskModel Bo3 MiniOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
47
MiniMax M2.5 only
21
o3 Mini only
24
Like-for-like categories
7 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
MiniMax M2.5 37.2 from 3 benchmarks, o3 Mini not benchmarked.
Widest category
Agentic work, 64.0 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: MiniMax M2.5 95.3% against o3 Mini 31.3%, 64.0 points apart on a 0 to 100 scale.
Output price
MiniMax M2.5 $1.20 against o3 Mini $4.40 per million output tokens, 3.7x apart.
Context window
MiniMax M2.5 takes 205K tokens, o3 Mini 200K.

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
CategoryMiniMax M2.5Barso3 MiniTies
Coding50
Intelligence20
Agentic work10
Reasoning80
Math12
Knowledge72
General172
All shared boards416
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for MiniMax M2.5 and o3 Mini
BenchmarkMiniMax M2.5o3 MiniLeader
Aider polyglotNot measured60.4%Only o3 Mini measured
SWE-bench Verified75.8%42.4%MiniMax M2.5
SWE-bench LiteNot measured32.3%Only o3 Mini measured
SWE-bench Multilingual68.3%Not measuredOnly MiniMax M2.5 measured
LMArena WebDev1386Not measuredOnly MiniMax M2.5 measured
LiveCodeBench (Vals AI)79.2%71.5%MiniMax M2.5
SWE-bench Verified (Vals AI)74.2%Not measuredOnly MiniMax M2.5 measured
Vibe Code Bench (Vals AI)14.8%Not measuredOnly MiniMax M2.5 measured
LiveCodeBench (Artificial Analysis run)Not measured73.4%Only o3 Mini measured
SciCodeNot measured42.8%Only o3 Mini measured
Terminal-Bench Hard (Artificial Analysis run)34.8%6.8%MiniMax M2.5
Terminal-Bench42.7%Not measuredOnly MiniMax M2.5 measured
GSO-BenchNot measured1.3%Only o3 Mini measured
WeirdMLNot measured43.7%Only o3 Mini measured
CybenchNot measured22.5%Only o3 Mini measured
ALE-Bench618.2Not measuredOnly MiniMax M2.5 measured
LMArena Text: coding13801378MiniMax M2.5
LMArena Text: software and IT13831364MiniMax M2.5
LMArena WebDev: React1374Not measuredOnly MiniMax M2.5 measured
LMArena WebDev: HTML1414Not measuredOnly MiniMax M2.5 measured
SciCodeNot measured7.7%Only o3 Mini measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for MiniMax M2.5 and o3 Mini
BenchmarkMiniMax M2.5o3 MiniLeader
AA Intelligence Index22.812.5MiniMax M2.5
Epoch Capabilities Index146.6140.2MiniMax M2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for MiniMax M2.5 and o3 Mini
BenchmarkMiniMax M2.5o3 MiniLeader
τ²-Bench Telecom95.3%31.3%MiniMax M2.5
Vending-Bench 2-$23Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
Reasoning benchmarks for MiniMax M2.5 and o3 Mini
BenchmarkMiniMax M2.5o3 MiniLeader
GPQA Diamond82.1%75.5%MiniMax M2.5
GPQA Diamond (Artificial Analysis run)84.8%77.3%MiniMax M2.5
Humanity's Last Exam (Artificial Analysis run)20.5%12.0%MiniMax M2.5
GPQA Diamond (Epoch AI run)Not measured77.0%Only o3 Mini measured
ARC-AGI63.7%34.5%MiniMax M2.5
ARC-AGI-24.9%3.0%MiniMax M2.5
SimpleBenchNot measured22.8%Only o3 Mini measured
Chess puzzlesNot measured15.0%Only o3 Mini measured
Mystery game puzzlesNot measured7.0%Only o3 Mini measured
LMArena Text: hard prompts13721365MiniMax M2.5
LMArena Text: expert13781364MiniMax M2.5
LMArena Text: hard prompts in English13841375MiniMax M2.5
Kagi LLM Benchmark55.2%Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index12
Math benchmarks for MiniMax M2.5 and o3 Mini
BenchmarkMiniMax M2.5o3 MiniLeader
AIME88.8%86.5%MiniMax M2.5
MATH 500 (Vals AI)Not measured91.8%Only o3 Mini measured
MGSM (Vals AI)Not measured91.3%Only o3 Mini measured
OTIS Mock AIMENot measured76.9%Only o3 Mini measured
FrontierMath, tiers 1 to 3Not measured18.6%Only o3 Mini measured
FrontierMath, tier 4Not measured0.0%Only o3 Mini measured
ProofBench4.0%Not measuredOnly MiniMax M2.5 measured
MATH level 5Not measured96.5%Only o3 Mini measured
LMArena Text: math13781396o3 Mini
LMArena Text: mathematical work13781399o3 Mini
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index72
Knowledge benchmarks for MiniMax M2.5 and o3 Mini
BenchmarkMiniMax M2.5o3 MiniLeader
MMLU Pro80.1%78.7%MiniMax M2.5
LegalBench (Vals AI)80.0%71.5%MiniMax M2.5
CaseLaw (Vals AI)53.5%Not measuredOnly MiniMax M2.5 measured
CorpFin (Vals AI)59.6%45.3%MiniMax M2.5
TaxEval (Vals AI)68.2%69.4%o3 Mini
MedQA (Vals AI)92.5%94.8%o3 Mini
MMLU Pro (Artificial Analysis run)Not measured80.2%Only o3 Mini measured
SimpleQA VerifiedNot measured15.3%Only o3 Mini measured
LMArena Text: science13691339MiniMax M2.5
LMArena Text: medicine and healthcare13571330MiniMax M2.5
LMArena Text: legal and government13661328MiniMax M2.5
LMArena Text: business and finance13561313MiniMax M2.5
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for MiniMax M2.5 and o3 Mini
BenchmarkMiniMax M2.5o3 MiniLeader
Design Arena: websites1222Not measuredOnly MiniMax M2.5 measured
Design Arena: UI components1173Not measuredOnly MiniMax M2.5 measured
Design Arena: game dev1176Not measuredOnly MiniMax M2.5 measured
Design Arena: data viz1172Not measuredOnly MiniMax M2.5 measured
Design Arena: 3D1170Not measuredOnly MiniMax M2.5 measured
Design Arena: all code categories1207Not measuredOnly MiniMax M2.5 measured
Design Arena: SVG1150Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index172
General benchmarks for MiniMax M2.5 and o3 Mini
BenchmarkMiniMax M2.5o3 MiniLeader
IFBench71.6%67.1%MiniMax M2.5
Long context reasoning (AA-LCR)73.3%43.0%MiniMax M2.5
DTBenchNot measured68.8%Only o3 Mini measured
LMCANot measured19.0%Only o3 Mini measured
Fiction.LiveBenchNot measured50.0%Only o3 Mini measured
Creative writing (Lech Mazur)Not measured61.7%Only o3 Mini measured
CL-bench11.4%Not measuredOnly MiniMax M2.5 measured
CL-bench Life6.3%Not measuredOnly MiniMax M2.5 measured
LMArena Text13591337MiniMax M2.5
LMArena Text: instruction following13531337MiniMax M2.5
LMArena Text: creative writing13311286MiniMax M2.5
LMArena Text: English13801351MiniMax M2.5
LMArena Text: non-English13381319MiniMax M2.5
LMArena Text: Chinese13931379MiniMax M2.5
LMArena Text: German13611303MiniMax M2.5
LMArena Text: Japanese11711286o3 Mini
LMArena Text: Korean12331313o3 Mini
LMArena Text: French13631334MiniMax M2.5
LMArena Text: Spanish13531321MiniMax M2.5
LMArena Text: Russian13591304MiniMax M2.5
LMArena Text: Polish13341294MiniMax M2.5
LMArena Text: multi-turn13641320MiniMax M2.5
LMArena Text: longer queries13661343MiniMax M2.5
LMArena Text: writing and language13451313MiniMax M2.5
LMArena Text: entertainment and media13291283MiniMax M2.5
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2.5 and o3 Mini
BenchmarkMiniMax M2.5o3 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

MiniMax M2.5$0.0009Fits in one request
o3 Mini$0.0033Fits in one request

MiniMax M2.5 costs less

Repository review

50K input + 3K output tokens

MiniMax M2.5$0.019Fits in one request
o3 Mini$0.068Fits in one request

MiniMax M2.5 costs less

Agent loop

200K input + 10K output tokens

MiniMax M2.5$0.072Exceeds the context window
o3 Mini$0.264Exceeds 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 MiniMax M2.5 and o3 Mini
SpecificationMiniMax M2.5OpenAI o3 Mini
MakerMiniMaxOpenAI
WeightsOpen weightsNo public weights listed
ReleasedFebruary 12, 2026January 31, 2025
Context window205K200K
Input $/Mtok$0.30$1.10
Output $/Mtok$1.20$4.40
Coding index37.2Not benchmarked
Independent measurements behind it30
Cost per solved task$0.62Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2.5 better than o3 Mini for coding?

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; o3 Mini has none, so the two cannot be ranked on coding. Pick o3 Mini for work measured by LMArena Text: math or LMArena Text: mathematical work, where it leads.

Which is cheaper, MiniMax M2.5 or o3 Mini?

MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; o3 Mini costs $1.10 and $4.40. Cost per solved task is known for MiniMax M2.5 only.

Which has the bigger context window, MiniMax M2.5 or o3 Mini?

MiniMax M2.5, with 205K tokens against 200K.

How many benchmarks is the MiniMax M2.5 vs o3 Mini comparison based on?

47 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and o3 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next