LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-4.1 Mini 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 GPT-4.1 Mini Replace MiniMax M2.5
GPT-4.1 MiniOpenAI
Coding
28.5
Overall
10.2
Output $/M
$1.60
3
MiniMax M2.5MiniMax
Coding
59.4
Overall
22.8
Output $/M
$0.95
50
vs boards won of 53 shared

Decision reading

Pick MiniMax M2.5 for coding: it scores 59.4 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 205K tokens, or when what matters is TaxEval (Vals AI) or LMArena Text: Japanese, where it leads.

Model AGPT-4.1 MiniOpenAI28.5/1002 independent benchmarks$1.818 per solved taskModel BMiniMax M2.5MiniMax59.4/1002 independent benchmarks$0.62 per solved task
Shared results
53
GPT-4.1 Mini only
31
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
GPT-4.1 Mini 28.5 from 2 benchmarks, MiniMax M2.5 59.4 from 2 benchmarks.
Widest category
Agentic work, 42.4 points apart on average over 1 shared benchmark.
Widest single gap
ARC-AGI: GPT-4.1 Mini 3.5% against MiniMax M2.5 63.7%, 60.2 points apart on a 0 to 100 scale.
Output price
GPT-4.1 Mini $1.60 against MiniMax M2.5 $0.95 per million output tokens, 1.7x apart.
Context window
GPT-4.1 Mini 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
CategoryGPT-4.1 MiniBarsMiniMax M2.5Ties
Coding05
Intelligence02
Agentic work01
Reasoning08
Math03
Knowledge18
Web design06
General217
All shared boards350
CodingLike-for-likeFour of these boards feed the Vibe Coding Index05
Coding benchmarks for GPT-4.1 Mini and MiniMax M2.5
BenchmarkGPT-4.1 MiniMiniMax M2.5Leader
Aider polyglot32.4%Not measuredOnly GPT-4.1 Mini measured
SWE-bench Verified23.9%75.8%MiniMax M2.5
SWE-bench MultilingualNot measured68.3%Only MiniMax M2.5 measured
LMArena WebDevNot measured1386Only MiniMax M2.5 measured
AA Coding Index20.2Not measuredOnly GPT-4.1 Mini measured
LiveCodeBench (Vals AI)58.2%79.2%MiniMax M2.5
SWE-bench Verified (Vals AI)Not measured74.2%Only MiniMax M2.5 measured
Vibe Code Bench (Vals AI)Not measured14.8%Only MiniMax M2.5 measured
LiveCodeBench (Artificial Analysis run)48.3%Not measuredOnly GPT-4.1 Mini measured
Terminal-Bench Hard (Artificial Analysis run)7.6%34.8%MiniMax M2.5
Terminal-BenchNot measured42.7%Only MiniMax M2.5 measured
WeirdML37.6%Not measuredOnly GPT-4.1 Mini measured
ALE-BenchNot measured618.2Only MiniMax M2.5 measured
LMArena Text: coding13671380MiniMax M2.5
LMArena Text: software and IT13601383MiniMax M2.5
LMArena WebDev: ReactNot measured1374Only MiniMax M2.5 measured
LMArena WebDev: HTMLNot measured1414Only MiniMax M2.5 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GPT-4.1 Mini and MiniMax M2.5
BenchmarkGPT-4.1 MiniMiniMax M2.5Leader
AA Intelligence Index10.222.8MiniMax M2.5
Epoch Capabilities Index134.9146.6MiniMax M2.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-4.1 Mini and MiniMax M2.5
BenchmarkGPT-4.1 MiniMiniMax M2.5Leader
τ²-Bench Telecom52.9%95.3%MiniMax M2.5
Vending-Bench 2Not measured-$23Only MiniMax M2.5 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for GPT-4.1 Mini and MiniMax M2.5
BenchmarkGPT-4.1 MiniMiniMax M2.5Leader
GPQA Diamond67.9%82.1%MiniMax M2.5
MMMU Pro (Vals AI)70.5%Not measuredOnly GPT-4.1 Mini measured
GPQA Diamond (Artificial Analysis run)66.4%84.8%MiniMax M2.5
Humanity's Last Exam (Artificial Analysis run)5.0%20.5%MiniMax M2.5
GPQA Diamond (Epoch AI run)65.8%Not measuredOnly GPT-4.1 Mini measured
ARC-AGI3.5%63.7%MiniMax M2.5
ARC-AGI-20.0%4.9%MiniMax M2.5
Chess puzzles1.0%Not measuredOnly GPT-4.1 Mini measured
Mystery game puzzles7.0%Not measuredOnly GPT-4.1 Mini measured
LMArena Text: hard prompts13491372MiniMax M2.5
LMArena Text: expert13381378MiniMax M2.5
LMArena Text: hard prompts in English13621384MiniMax M2.5
LMArena Vision: diagrams1182Not measuredOnly GPT-4.1 Mini measured
LMArena Vision: homework1214Not measuredOnly 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 index03
Math benchmarks for GPT-4.1 Mini and MiniMax M2.5
BenchmarkGPT-4.1 MiniMiniMax M2.5Leader
AIME49.4%88.8%MiniMax M2.5
MATH 500 (Vals AI)88.0%Not measuredOnly GPT-4.1 Mini measured
MGSM (Vals AI)87.8%Not measuredOnly GPT-4.1 Mini measured
AA Math Index46.3Not measuredOnly GPT-4.1 Mini measured
AIME 2025 (Artificial Analysis run)46.3%Not measuredOnly GPT-4.1 Mini measured
OTIS Mock AIME44.7%Not measuredOnly GPT-4.1 Mini measured
FrontierMath, tiers 1 to 36.7%Not measuredOnly GPT-4.1 Mini measured
ProofBenchNot measured4.0%Only MiniMax M2.5 measured
MATH level 587.3%Not measuredOnly GPT-4.1 Mini measured
LMArena Text: math13431378MiniMax M2.5
LMArena Text: mathematical work13471378MiniMax M2.5
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index18
Knowledge benchmarks for GPT-4.1 Mini and MiniMax M2.5
BenchmarkGPT-4.1 MiniMiniMax M2.5Leader
MMLU Pro77.2%80.1%MiniMax M2.5
LegalBench (Vals AI)78.0%80.0%MiniMax M2.5
CaseLaw (Vals AI)Not measured53.5%Only MiniMax M2.5 measured
CorpFin (Vals AI)57.9%59.6%MiniMax M2.5
TaxEval (Vals AI)71.9%68.2%GPT-4.1 Mini
MortgageTax (Vals AI)65.5%Not measuredOnly GPT-4.1 Mini measured
MedQA (Vals AI)84.6%92.5%MiniMax M2.5
MMLU Pro (Artificial Analysis run)78.1%Not measuredOnly GPT-4.1 Mini measured
SimpleQA Verified12.7%Not measuredOnly GPT-4.1 Mini measured
LMArena Text: science13281369MiniMax M2.5
LMArena Text: medicine and healthcare13241357MiniMax M2.5
LMArena Text: legal and government13431366MiniMax M2.5
LMArena Text: business and finance13221356MiniMax M2.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index06
Web design benchmarks for GPT-4.1 Mini and MiniMax M2.5
BenchmarkGPT-4.1 MiniMiniMax M2.5Leader
Design Arena: websites9971222MiniMax M2.5
Design Arena: UI components9611172MiniMax M2.5
Design Arena: game dev10711176MiniMax M2.5
Design Arena: data viz10341171MiniMax M2.5
Design Arena: 3D8371170MiniMax M2.5
Design Arena: all code categories9941207MiniMax M2.5
Design Arena: SVGNot measured1147Only 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 index217
General benchmarks for GPT-4.1 Mini and MiniMax M2.5
BenchmarkGPT-4.1 MiniMiniMax M2.5Leader
IFBench38.3%71.6%MiniMax M2.5
Long context reasoning (AA-LCR)44.0%73.3%MiniMax M2.5
DTBench68.8%Not measuredOnly GPT-4.1 Mini measured
LMCA21.1%Not measuredOnly GPT-4.1 Mini measured
Fiction.LiveBench44.4%Not measuredOnly GPT-4.1 Mini measured
CL-benchNot measured11.4%Only MiniMax M2.5 measured
CL-bench LifeNot measured6.3%Only MiniMax M2.5 measured
LMArena Text13411359MiniMax M2.5
LMArena Text: instruction following13331353MiniMax M2.5
LMArena Text: creative writing12991331MiniMax M2.5
LMArena Vision1181Not measuredOnly GPT-4.1 Mini measured
LMArena Text: English13561380MiniMax M2.5
LMArena Text: non-English13181338MiniMax M2.5
LMArena Text: Chinese13291393MiniMax M2.5
LMArena Text: German13501361MiniMax M2.5
LMArena Text: Japanese12901171GPT-4.1 Mini
LMArena Text: Korean12981233GPT-4.1 Mini
LMArena Text: French13581363MiniMax M2.5
LMArena Text: Spanish13191353MiniMax M2.5
LMArena Text: Russian13241359MiniMax M2.5
LMArena Text: Polish13261334MiniMax M2.5
LMArena Text: multi-turn13541364MiniMax M2.5
LMArena Text: longer queries13441366MiniMax M2.5
LMArena Text: writing and language13191345MiniMax M2.5
LMArena Text: entertainment and media13001329MiniMax M2.5
LMArena Vision: English1191Not measuredOnly GPT-4.1 Mini measured
LMArena Vision: Chinese1186Not measuredOnly GPT-4.1 Mini measured
LMArena Vision: reading text1188Not measuredOnly GPT-4.1 Mini measured
LMArena Vision: humor1182Not measuredOnly GPT-4.1 Mini measured
LMArena Vision: captioning1174Not measuredOnly GPT-4.1 Mini measured
LMArena Vision: recognizing things1187Not measuredOnly GPT-4.1 Mini measured
LMArena Vision: creative writing1182Not measuredOnly 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 GPT-4.1 Mini and MiniMax M2.5
BenchmarkGPT-4.1 MiniMiniMax 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

GPT-4.1 Mini$0.0012Fits in one request
MiniMax M2.5$0.0007Fits in one request

MiniMax M2.5 costs less

Repository review

50K input + 3K output tokens

GPT-4.1 Mini$0.025Fits in one request
MiniMax M2.5$0.016Fits in one request

MiniMax M2.5 costs less

Agent loop

200K input + 10K output tokens

GPT-4.1 Mini$0.096Fits 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 GPT-4.1 Mini and MiniMax M2.5
SpecificationOpenAI GPT-4.1 MiniMiniMax M2.5
MakerOpenAIMiniMax
WeightsNo public weights listedOpen weights
ReleasedApril 14, 2025February 12, 2026
Context window1.05M205K
Input $/Mtok$0.40$0.27
Output $/Mtok$1.60$0.95
Coding index28.559.4
Independent measurements behind it22
Cost per solved task$1.818$0.62
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 Mini better than MiniMax M2.5 for coding?

Pick MiniMax M2.5 for coding: it scores 59.4 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 205K tokens, or when what matters is TaxEval (Vals AI) or LMArena Text: Japanese, where it leads.

Which is cheaper, GPT-4.1 Mini or MiniMax M2.5?

GPT-4.1 Mini costs $0.40 per million input tokens and $1.60 per million output tokens; MiniMax M2.5 costs $0.27 and $0.95. Per solved SWE-bench Verified task, GPT-4.1 Mini costs $1.818 and MiniMax M2.5 $0.62.

Which has the bigger context window, GPT-4.1 Mini or MiniMax M2.5?

GPT-4.1 Mini, with 1.05M tokens against 205K.

How many benchmarks is the GPT-4.1 Mini vs MiniMax M2.5 comparison based on?

53 benchmarks have a result for both models as of October 21, 2026. GPT-4.1 Mini's coding index rests on 2 independent benchmarks 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

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/gpt-4-1-mini-vs-minimax-minimax-m2-5" title="GPT-4.1 Mini vs MiniMax M2.5, 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/gpt-4-1-mini-vs-minimax-minimax-m2-5">LLMBenchmark.ai, GPT-4.1 Mini vs MiniMax M2.5</a></p>