Enter opens the highlighted result. Esc closes.

GPT-5.1 vs MiniMax M3

GPT-5.1 leads MiniMax M3 on coding, 40.4 to 39.2 on the Vibe Coding Index, and MiniMax M3 costs 8.3x less per output token ($1.20 vs $10.00 per million). Updated October 22, 2026; 80 benchmarks have a result for both.

Replace GPT-5.1 Replace MiniMax M3
GPT-5.1OpenAI
Coding
40.4
Overall
55.0
Output $/M
$10.00
44
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
36
vs boards won of 80 shared

GPT-5.1 or MiniMax M3: which to pick

GPT-5.1 and MiniMax M3 are level for coding, 40.4 against 39.2 on the Vibe Coding Index, so price and context decide.

Pick MiniMax M3 for output tokens 8.3x cheaper ($1.20 vs $10.00 per million) and a lower cost per solved task ($0.56 against $1.02). Pick GPT-5.1 for work measured by LiveCodeBench (Vals AI) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model AGPT-5.1OpenAI40.4/1003 independent benchmarks$1.02 per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
80
GPT-5.1 only
21
MiniMax M3 only
36
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
GPT-5.1 40.4 from 3 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Coding, 9.7 points apart on average over 11 shared benchmarks.
Widest single gap
Chess puzzles: GPT-5.1 42.0% against MiniMax M3 13.0%, 29.0 points apart on a 0 to 100 scale.
Output price
GPT-5.1 $10.00 against MiniMax M3 $1.20 per million output tokens, 8.3x apart.
Context window
GPT-5.1 takes 400K tokens, MiniMax M3 1.05M.

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-5.1BarsMiniMax M3Ties
Coding29
Intelligence11
Agentic work02
Reasoning85
Math30
Knowledge73
Web design08
General238
All shared boards4436
CodingLike-for-likeSix of these boards feed the Vibe Coding Index29
Coding benchmarks for GPT-5.1 and MiniMax M3
BenchmarkGPT-5.1MiniMax M3Leader
SWE-bench Verified66.0%Not measuredOnly GPT-5.1 measured
LiveBench codingNot measured70.9%Only MiniMax M3 measured
LMArena WebDev13961482MiniMax M3
AA Coding Index49.458.6MiniMax M3
LiveCodeBench (Vals AI)86.5%82.2%GPT-5.1
SWE-bench Verified (Vals AI)69.8%75.0%MiniMax M3
Terminal-Bench 4 (Vals AI)Not measured1.0%Only MiniMax M3 measured
Vibe Code Bench (Vals AI)24.6%47.6%MiniMax M3
Code migration (Vals AI)Not measured19.9%Only MiniMax M3 measured
Terminal-Bench 2.1 (Vals AI)Not measured53.6%Only MiniMax M3 measured
SWE-bench Multimodal (Vals AI)Not measured33.3%Only MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured9.2%Only MiniMax M3 measured
SkillsBench (Vals AI)Not measured51.5%Only MiniMax M3 measured
CyberBench (Vals AI)Not measured65.0%Only MiniMax M3 measured
LiveCodeBench (Artificial Analysis run)86.8%Not measuredOnly GPT-5.1 measured
SciCodeNot measured47.1%Only MiniMax M3 measured
Terminal-Bench Hard (Artificial Analysis run)45.5%42.4%GPT-5.1
Terminal-Bench47.6%Not measuredOnly GPT-5.1 measured
FrontierCodeNot measured14.7%Only MiniMax M3 measured
GSO-Bench13.7%Not measuredOnly GPT-5.1 measured
WeirdML60.8%Not measuredOnly GPT-5.1 measured
ALE-BenchNot measured640.0Only MiniMax M3 measured
LMArena Text: coding14531470MiniMax M3
LMArena Text: software and IT14541466MiniMax M3
LMArena WebDev: React13071478MiniMax M3
LMArena WebDev: HTML14051455MiniMax M3
LMArena WebDev: from an image14211470MiniMax M3
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for GPT-5.1 and MiniMax M3
BenchmarkGPT-5.1MiniMax M3Leader
AA Intelligence Index24.729.2MiniMax M3
Epoch Capabilities Index149.8146.9GPT-5.1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for GPT-5.1 and MiniMax M3
BenchmarkGPT-5.1MiniMax M3Leader
AA Agentic IndexNot measured29.5Only MiniMax M3 measured
Design Arena: agents building web appsNot measured1200Only MiniMax M3 measured
Design Arena: agents building full-stack appsNot measured1197Only MiniMax M3 measured
Design Arena: agents building mobile appsNot measured1169Only MiniMax M3 measured
Design Arena: agents building Android appsNot measured1159Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1158Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1130Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1181Only MiniMax M3 measured
Design Arena: spreadsheetsNot measured1028Only MiniMax M3 measured
LiveBench researchNot measured68.0%Only MiniMax M3 measured
LiveBench browserNot measured8.0%Only MiniMax M3 measured
LiveBench long agenticNot measured12.4%Only MiniMax M3 measured
Finance Agent (Vals AI)Not measured48.3%Only MiniMax M3 measured
Tax Agent Bench (Vals AI)Not measured20.6%Only MiniMax M3 measured
Legal Research Bench (Vals AI)Not measured29.8%Only MiniMax M3 measured
Excel Modeling Benchmark (Vals AI)Not measured47.8%Only MiniMax M3 measured
τ²-Bench Telecom81.9%88.9%MiniMax M3
APEX-AgentsNot measured37.7%Only MiniMax M3 measured
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
DeepResearch Bench42.8%Not measuredOnly GPT-5.1 measured
Vending-Bench 2$1,473$2,158MiniMax M3
Neither model has a result on the other 20 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index85
Reasoning benchmarks for GPT-5.1 and MiniMax M3
BenchmarkGPT-5.1MiniMax M3Leader
GPQA Diamond86.6%92.7%MiniMax M3
LiveBench reasoningNot measured74.5%Only MiniMax M3 measured
MMMU Pro (Vals AI)83.2%81.2%GPT-5.1
GPQA Diamond (Artificial Analysis run)87.3%92.9%MiniMax M3
Humanity's Last Exam (Artificial Analysis run)28.5%39.0%MiniMax M3
GPQA Diamond (Epoch AI run)87.6%90.9%MiniMax M3
ARC-AGI72.8%Not measuredOnly GPT-5.1 measured
ARC-AGI-217.6%Not measuredOnly GPT-5.1 measured
SimpleBench53.2%45.8%GPT-5.1
Chess puzzles42.0%13.0%GPT-5.1
Mystery game puzzles19.0%8.0%GPT-5.1
VPCT58.7%Not measuredOnly GPT-5.1 measured
LMArena Text: hard prompts14571447GPT-5.1
LMArena Text: expert14701461GPT-5.1
LMArena Text: hard prompts in English14621455GPT-5.1
LMArena Vision: diagrams12641266MiniMax M3
LMArena Vision: homework12721268GPT-5.1
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for GPT-5.1 and MiniMax M3
BenchmarkGPT-5.1MiniMax M3Leader
AIME93.3%Not measuredOnly GPT-5.1 measured
MGSM (Vals AI)93.0%Not measuredOnly GPT-5.1 measured
AA Math Index94.0Not measuredOnly GPT-5.1 measured
AIME 2025 (Artificial Analysis run)94.0%Not measuredOnly GPT-5.1 measured
OTIS Mock AIME88.6%71.1%GPT-5.1
ProofBenchNot measured18.0%Only MiniMax M3 measured
LMArena Text: math14461429GPT-5.1
LMArena Text: mathematical work14491448GPT-5.1
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index73
Knowledge benchmarks for GPT-5.1 and MiniMax M3
BenchmarkGPT-5.1MiniMax M3Leader
MMLU Pro86.4%84.2%GPT-5.1
LegalBench (Vals AI)85.7%85.4%GPT-5.1
CaseLaw (Vals AI)73.4%Not measuredOnly GPT-5.1 measured
CorpFin (Vals AI)63.8%68.1%MiniMax M3
TaxEval (Vals AI)74.9%72.7%GPT-5.1
MortgageTax (Vals AI)61.4%68.4%MiniMax M3
MedQA (Vals AI)96.4%Not measuredOnly GPT-5.1 measured
MedCode (Vals AI)52.7%46.3%GPT-5.1
MMLU Pro (Artificial Analysis run)87.0%Not measuredOnly GPT-5.1 measured
SimpleQA Verified48.0%Not measuredOnly GPT-5.1 measured
LMArena Text: science14591452GPT-5.1
LMArena Text: medicine and healthcare14561441GPT-5.1
LMArena Text: legal and government14591437GPT-5.1
LMArena Text: business and finance14311434MiniMax M3
FACTS Benchmark Suite45.0%Not measuredOnly GPT-5.1 measured
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for GPT-5.1 and MiniMax M3
BenchmarkGPT-5.1MiniMax M3Leader
Design Arena: websites11871257MiniMax M3
Design Arena: UI components11631242MiniMax M3
Design Arena: game dev11781210MiniMax M3
Design Arena: data viz12041236MiniMax M3
Design Arena: 3D10601208MiniMax M3
Design Arena: all code categories11701247MiniMax M3
Design Arena: SVG11491161MiniMax M3
Design Arena: ASCII art11191161MiniMax M3
LiveBench designNot measured66.2%Only MiniMax M3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index238
General benchmarks for GPT-5.1 and MiniMax M3
BenchmarkGPT-5.1MiniMax M3Leader
LiveBench data analysisNot measured76.2%Only MiniMax M3 measured
Public Benefits Bench (Vals AI)Not measured64.1%Only MiniMax M3 measured
SAGE (Vals AI)43.2%50.6%MiniMax M3
MedScribe (Vals AI)88.1%87.3%GPT-5.1
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBench72.9%82.9%MiniMax M3
Long context reasoning (AA-LCR)80.0%83.0%MiniMax M3
DTBench90.1%78.9%GPT-5.1
LMCA43.9%33.7%GPT-5.1
CL-bench23.7%Not measuredOnly GPT-5.1 measured
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
CL-bench Life17.3%Not measuredOnly GPT-5.1 measured
LMArena Text14431433GPT-5.1
LMArena Text: instruction following14431433GPT-5.1
LMArena Text: creative writing14271404GPT-5.1
LMArena Vision12501251MiniMax M3
LMArena Text: English14511443GPT-5.1
LMArena Text: non-English14311420GPT-5.1
LMArena Text: Chinese14951466GPT-5.1
LMArena Text: German14381428GPT-5.1
LMArena Text: Japanese14531380GPT-5.1
LMArena Text: Korean14011373GPT-5.1
LMArena Text: French14501444GPT-5.1
LMArena Text: Spanish14331433GPT-5.1
LMArena Text: Russian14351426GPT-5.1
LMArena Text: Polish14401423GPT-5.1
LMArena Text: multi-turn14501443GPT-5.1
LMArena Text: longer queries14481446GPT-5.1
LMArena Text: writing and language14281419GPT-5.1
LMArena Text: entertainment and media14151403GPT-5.1
LMArena Vision: English12521263MiniMax M3
LMArena Vision: Chinese12701311MiniMax M3
LMArena Vision: reading text12551259MiniMax M3
LMArena Vision: humor12631235GPT-5.1
LMArena Vision: captioning1252Not measuredOnly GPT-5.1 measured
LMArena Vision: recognizing things12321197GPT-5.1
LMArena Vision: creative writing12661234GPT-5.1
LMArena Document14031435MiniMax M3
Neither model has a result on the other 8 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.1 and MiniMax M3
BenchmarkGPT-5.1MiniMax M3Leader
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-5.1$0.0063Fits in one request
MiniMax M3$0.0009Fits in one request

MiniMax M3 costs less

Repository review

50K input + 3K output tokens

GPT-5.1$0.092Fits in one request
MiniMax M3$0.019Fits in one request

MiniMax M3 costs less

Agent loop

200K input + 10K output tokens

GPT-5.1$0.350Fits in one request
MiniMax M3$0.072Fits in one request

MiniMax M3 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-5.1 and MiniMax M3
SpecificationOpenAI GPT-5.1MiniMax M3
MakerOpenAIMiniMax
WeightsNo public weights listedOpen weights
ReleasedNovember 13, 2025May 31, 2026
Context window400K1.05M
Input $/Mtok$1.25$0.30
Output $/Mtok$10.00$1.20
Coding index40.439.2
Independent measurements behind it36
Cost per solved task$1.02$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.1 better than MiniMax M3 for coding?

GPT-5.1 and MiniMax M3 are level for coding, 40.4 against 39.2 on the Vibe Coding Index, so price and context decide. Pick MiniMax M3 for output tokens 8.3x cheaper ($1.20 vs $10.00 per million) and a lower cost per solved task ($0.56 against $1.02). Pick GPT-5.1 for work measured by LiveCodeBench (Vals AI) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, GPT-5.1 or MiniMax M3?

GPT-5.1 costs $1.25 per million input tokens and $10.00 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Per solved SWE-bench Verified task, GPT-5.1 costs $1.02 and MiniMax M3 $0.56.

Which has the bigger context window, GPT-5.1 or MiniMax M3?

MiniMax M3, with 1.05M tokens against 400K.

How many benchmarks is the GPT-5.1 vs MiniMax M3 comparison based on?

80 benchmarks have a result for both models as of October 22, 2026. GPT-5.1's coding index rests on 3 independent benchmarks and MiniMax M3's on 6. 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-5-1-vs-minimax-minimax-m3" title="GPT-5.1 vs MiniMax M3, 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-5-1-vs-minimax-minimax-m3">LLMBenchmark.ai, GPT-5.1 vs MiniMax M3</a></p>