LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-5.1-Codex-Mini vs MiniMax M2

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

Replace GPT-5.1-Codex-Mini Replace MiniMax M2
GPT-5.1-Codex-MiniOpenAI
Coding
6.2
Overall
20.4
Output $/M
$2.00
9
MiniMax M2MiniMax
Coding
45.3
Overall
18.6
Output $/M
$1.02
11
vs boards won of 21 shared, 1 tied

Decision reading

Pick MiniMax M2 for coding: it scores 45.3 on the Vibe Coding Index against 6.2 for GPT-5.1-Codex-Mini.

Pick GPT-5.1-Codex-Mini when the context window is larger, 400K against 205K tokens, or when what matters is LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model AGPT-5.1-Codex-MiniOpenAI6.2/1001 independent benchmarkNo cost per solved taskModel BMiniMax M2MiniMax45.3/1002 independent benchmarks$0.702 per solved task
Shared results
21
GPT-5.1-Codex-Mini only
1
MiniMax M2 only
28
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-5.1-Codex-Mini 6.2 from 1 benchmark, MiniMax M2 45.3 from 2 benchmarks.
Widest category
Agentic work, 24.0 points apart on average over 1 shared benchmark.
Widest single gap
Terminal-Bench: GPT-5.1-Codex-Mini 61.6% against MiniMax M2 30.0%, 31.5 points apart on a 0 to 100 scale.
Output price
GPT-5.1-Codex-Mini $2.00 against MiniMax M2 $1.02 per million output tokens, 2.0x apart.
Context window
GPT-5.1-Codex-Mini takes 400K tokens, MiniMax M2 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-5.1-Codex-MiniBarsMiniMax M2Ties
Coding32
Intelligence10
Agentic work01
Reasoning20
Math20
Knowledge001 tie
Web design07
General11
All shared boards9111 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index32
Coding benchmarks for GPT-5.1-Codex-Mini and MiniMax M2
BenchmarkGPT-5.1-Codex-MiniMiniMax M2Leader
SWE-bench VerifiedNot measured61.0%Only MiniMax M2 measured
LMArena WebDev12441297MiniMax M2
LiveCodeBench (Artificial Analysis run)83.6%82.6%GPT-5.1-Codex-Mini
Terminal-Bench Hard (Artificial Analysis run)33.3%25.8%GPT-5.1-Codex-Mini
Terminal-Bench61.6%30.0%GPT-5.1-Codex-Mini
LMArena Text: codingNot measured1371Only MiniMax M2 measured
LMArena Text: software and ITNot measured1373Only MiniMax M2 measured
LMArena WebDev: HTML12531306MiniMax M2
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GPT-5.1-Codex-Mini and MiniMax M2
BenchmarkGPT-5.1-Codex-MiniMiniMax M2Leader
AA Intelligence Index20.418.6GPT-5.1-Codex-Mini
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GPT-5.1-Codex-Mini and MiniMax M2
BenchmarkGPT-5.1-Codex-MiniMiniMax M2Leader
τ²-Bench Telecom62.9%86.8%MiniMax M2
Vending-Bench 2Not measured$161Only MiniMax M2 measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for GPT-5.1-Codex-Mini and MiniMax M2
BenchmarkGPT-5.1-Codex-MiniMiniMax M2Leader
GPQA Diamond (Artificial Analysis run)81.3%77.7%GPT-5.1-Codex-Mini
Humanity's Last Exam (Artificial Analysis run)18.5%13.7%GPT-5.1-Codex-Mini
LMArena Text: hard promptsNot measured1357Only MiniMax M2 measured
LMArena Text: expertNot measured1338Only MiniMax M2 measured
LMArena Text: hard prompts in EnglishNot measured1376Only MiniMax M2 measured
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for GPT-5.1-Codex-Mini and MiniMax M2
BenchmarkGPT-5.1-Codex-MiniMiniMax M2Leader
AA Math Index91.778.3GPT-5.1-Codex-Mini
AIME 2025 (Artificial Analysis run)91.7%78.3%GPT-5.1-Codex-Mini
LMArena Text: mathNot measured1351Only MiniMax M2 measured
LMArena Text: mathematical workNot measured1368Only MiniMax M2 measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index00
Knowledge benchmarks for GPT-5.1-Codex-Mini and MiniMax M2
BenchmarkGPT-5.1-Codex-MiniMiniMax M2Leader
MMLU Pro (Artificial Analysis run)82.0%82.0%Tie
LMArena Text: scienceNot measured1348Only MiniMax M2 measured
LMArena Text: medicine and healthcareNot measured1367Only MiniMax M2 measured
LMArena Text: legal and governmentNot measured1349Only MiniMax M2 measured
LMArena Text: business and financeNot measured1336Only MiniMax M2 measured
Neither model has a result on the other 12 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for GPT-5.1-Codex-Mini and MiniMax M2
BenchmarkGPT-5.1-Codex-MiniMiniMax M2Leader
Design Arena: websites11111144MiniMax M2
Design Arena: UI components10811136MiniMax M2
Design Arena: game dev10931119MiniMax M2
Design Arena: data viz10971140MiniMax M2
Design Arena: 3D9881098MiniMax M2
Design Arena: all code categories10941135MiniMax M2
Design Arena: SVG9771098MiniMax M2
Design Arena: ASCII art1104Not measuredOnly GPT-5.1-Codex-Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
General benchmarks for GPT-5.1-Codex-Mini and MiniMax M2
BenchmarkGPT-5.1-Codex-MiniMiniMax M2Leader
IFBench67.9%72.3%MiniMax M2
Long context reasoning (AA-LCR)66.7%64.3%GPT-5.1-Codex-Mini
LMArena TextNot measured1340Only MiniMax M2 measured
LMArena Text: instruction followingNot measured1329Only MiniMax M2 measured
LMArena Text: creative writingNot measured1286Only MiniMax M2 measured
LMArena Text: EnglishNot measured1364Only MiniMax M2 measured
LMArena Text: non-EnglishNot measured1313Only MiniMax M2 measured
LMArena Text: ChineseNot measured1366Only MiniMax M2 measured
LMArena Text: GermanNot measured1357Only MiniMax M2 measured
LMArena Text: FrenchNot measured1336Only MiniMax M2 measured
LMArena Text: SpanishNot measured1326Only MiniMax M2 measured
LMArena Text: RussianNot measured1330Only MiniMax M2 measured
LMArena Text: PolishNot measured1312Only MiniMax M2 measured
LMArena Text: multi-turnNot measured1361Only MiniMax M2 measured
LMArena Text: longer queriesNot measured1331Only MiniMax M2 measured
LMArena Text: writing and languageNot measured1295Only MiniMax M2 measured
LMArena Text: entertainment and mediaNot measured1298Only MiniMax M2 measured
Neither model has a result on the other 29 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.1-Codex-Mini and MiniMax M2
BenchmarkGPT-5.1-Codex-MiniMiniMax M2Leader
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-Codex-Mini$0.0013Fits in one request
MiniMax M2$0.0008Fits in one request

MiniMax M2 costs less

Repository review

50K input + 3K output tokens

GPT-5.1-Codex-Mini$0.018Fits in one request
MiniMax M2$0.016Fits in one request

MiniMax M2 costs less

Agent loop

200K input + 10K output tokens

GPT-5.1-Codex-Mini$0.070Fits in one request
MiniMax M2$0.061Exceeds the context window

MiniMax M2 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-Codex-Mini and MiniMax M2
SpecificationOpenAI GPT-5.1-Codex-MiniMiniMax M2
MakerOpenAIMiniMax
WeightsNo public weights listedOpen weights
ReleasedNovember 13, 2025October 23, 2025
Context window400K205K
Input $/Mtok$0.25$0.255
Output $/Mtok$2.00$1.02
Coding index6.245.3
Independent measurements behind it12
Cost per solved taskNot computable$0.702
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.1-Codex-Mini better than MiniMax M2 for coding?

Pick MiniMax M2 for coding: it scores 45.3 on the Vibe Coding Index against 6.2 for GPT-5.1-Codex-Mini. Pick GPT-5.1-Codex-Mini when the context window is larger, 400K against 205K tokens, or when what matters is LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, GPT-5.1-Codex-Mini or MiniMax M2?

GPT-5.1-Codex-Mini costs $0.25 per million input tokens and $2.00 per million output tokens; MiniMax M2 costs $0.255 and $1.02. Cost per solved task is known for MiniMax M2 only.

Which has the bigger context window, GPT-5.1-Codex-Mini or MiniMax M2?

GPT-5.1-Codex-Mini, with 400K tokens against 205K.

How many benchmarks is the GPT-5.1-Codex-Mini vs MiniMax M2 comparison based on?

21 benchmarks have a result for both models as of October 21, 2026. GPT-5.1-Codex-Mini's coding index rests on 1 independent benchmark and MiniMax M2's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next