LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

MiniMax M2.7 vs Inkling Small

Updated October 21, 2026. 57 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace MiniMax M2.7 Replace Inkling Small
MiniMax M2.7MiniMax
Coding
28.4
Overall
22.8
Output $/M
$1.20
14
T Inkling SmallThinking Machines
Coding
29.9
Overall
25.7
Output $/M
$1.20
43
vs boards won of 57 shared

Decision reading

MiniMax M2.7 and Inkling Small are level for coding, 28.4 against 29.9 on the Vibe Coding Index, so price and context decide.

Pick MiniMax M2.7 when what matters is SciCode or LMArena Text: coding, where it leads. Pick Inkling Small when a solved task costs $0.16 against $0.64, or when the context window is larger, 524K against 205K tokens.

Model AMiniMax M2.7MiniMax28.4/1001 independent benchmark$0.64 per solved taskModel BInkling SmallThinking Machines29.9/1001 independent benchmark$0.16 per solved task
Shared results
57
MiniMax M2.7 only
17
Inkling Small only
27
Like-for-like categories
7 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
MiniMax M2.7 28.4 from 1 benchmark, Inkling Small 29.9 from 1 benchmark.
Widest category
Agentic work, 9.7 points apart on average over 5 shared benchmarks.
Widest single gap
LMArena Text: Japanese: MiniMax M2.7 1260 against Inkling Small 1401, 23.5 points apart on a 0 to 100 scale.
Output price
Both cost $1.20 per million output tokens.
Context window
MiniMax M2.7 takes 205K tokens, Inkling Small 524K.

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 M2.7BarsInkling SmallTies
Coding310
Intelligence02
Agentic work05
Reasoning33
Math03
Knowledge18
General712
All shared boards1443
CodingLike-for-likeFour of these boards feed the Vibe Coding Index310
Coding benchmarks for MiniMax M2.7 and Inkling Small
BenchmarkMiniMax M2.7Inkling SmallLeader
LMArena WebDev13991409Inkling Small
AA Coding Index52.652.9Inkling Small
LiveCodeBench (Vals AI)79.9%85.9%Inkling Small
SWE-bench Verified (Vals AI)73.8%82.2%Inkling Small
Terminal-Bench 4 (Vals AI)Not measured0.0%Only Inkling Small measured
Vibe Code Bench (Vals AI)11.9%19.1%Inkling Small
Code migration (Vals AI)8.7%13.7%Inkling Small
ProgramBench (Vals AI)0.0%0.5%Inkling Small
IOI (Vals AI)Not measured9.3%Only Inkling Small measured
Terminal-Bench 2.1 (Vals AI)48.7%55.1%Inkling Small
SkillsBench (Vals AI)Not measured33.6%Only Inkling Small measured
CyberBench (Vals AI)Not measured64.1%Only Inkling Small measured
SciCode50.1%49.7%MiniMax M2.7
Terminal-Bench Hard (Artificial Analysis run)39.4%Not measuredOnly MiniMax M2.7 measured
Terminal-Bench45.1%Not measuredOnly MiniMax M2.7 measured
WeirdML37.0%Not measuredOnly MiniMax M2.7 measured
ALE-Bench599.3Not measuredOnly MiniMax M2.7 measured
LMArena Text: coding14541450MiniMax M2.7
LMArena Text: software and IT14461447Inkling Small
LMArena WebDev: React13881399Inkling Small
LMArena WebDev: HTML14011398MiniMax M2.7
LMArena WebDev: from an imageNot measured1410Only Inkling Small measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for MiniMax M2.7 and Inkling Small
BenchmarkMiniMax M2.7Inkling SmallLeader
AA Intelligence Index22.825.7Inkling Small
Epoch Capabilities Index145.8150.3Inkling Small
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
Agentic work benchmarks for MiniMax M2.7 and Inkling Small
BenchmarkMiniMax M2.7Inkling SmallLeader
AA Agentic Index15.323.5Inkling Small
Finance Agent (Vals AI)27.9%41.3%Inkling Small
Tax Agent Bench (Vals AI)6.9%15.4%Inkling Small
Legal Research Bench (Vals AI)10.6%25.5%Inkling Small
Harvey's Legal Agent Benchmark (Vals AI)Not measured2.9%Only Inkling Small measured
Excel Modeling Benchmark (Vals AI)28.4%31.8%Inkling Small
τ²-Bench Telecom84.8%Not measuredOnly MiniMax M2.7 measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
Reasoning benchmarks for MiniMax M2.7 and Inkling Small
BenchmarkMiniMax M2.7Inkling SmallLeader
GPQA Diamond86.6%83.6%MiniMax M2.7
GPQA Diamond (Artificial Analysis run)87.4%89.5%Inkling Small
Humanity's Last Exam (Artificial Analysis run)29.6%33.3%Inkling Small
GPQA Diamond (Epoch AI run)Not measured88.5%Only Inkling Small measured
ARC-AGINot measured84.0%Only Inkling Small measured
ARC-AGI-2Not measured40.1%Only Inkling Small measured
Mystery game puzzlesNot measured6.0%Only Inkling Small measured
LMArena Text: hard prompts14221423Inkling Small
LMArena Text: expert14431441MiniMax M2.7
LMArena Text: hard prompts in English14411429MiniMax M2.7
LMArena Vision: diagramsNot measured1251Only Inkling Small measured
LMArena Vision: homeworkNot measured1257Only Inkling Small measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for MiniMax M2.7 and Inkling Small
BenchmarkMiniMax M2.7Inkling SmallLeader
AIME91.0%Not measuredOnly MiniMax M2.7 measured
OTIS Mock AIMENot measured90.0%Only Inkling Small measured
FrontierMath, tiers 1 to 3Not measured46.3%Only Inkling Small measured
FrontierMath, tier 4Not measured17.1%Only Inkling Small measured
ProofBench3.0%6.0%Inkling Small
LMArena Text: math14211459Inkling Small
LMArena Text: mathematical work14371441Inkling Small
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index18
Knowledge benchmarks for MiniMax M2.7 and Inkling Small
BenchmarkMiniMax M2.7Inkling SmallLeader
MMLU Pro80.4%85.6%Inkling Small
LegalBench (Vals AI)84.0%83.0%MiniMax M2.7
CaseLaw (Vals AI)60.9%Not measuredOnly MiniMax M2.7 measured
CorpFin (Vals AI)61.2%69.6%Inkling Small
TaxEval (Vals AI)66.6%75.5%Inkling Small
MortgageTax (Vals AI)Not measured62.3%Only Inkling Small measured
MedCode (Vals AI)34.4%37.9%Inkling Small
SimpleQA VerifiedNot measured19.1%Only Inkling Small measured
LMArena Text: science14161428Inkling Small
LMArena Text: medicine and healthcare14091413Inkling Small
LMArena Text: legal and government14031415Inkling Small
LMArena Text: business and finance14071413Inkling Small
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for MiniMax M2.7 and Inkling Small
BenchmarkMiniMax M2.7Inkling SmallLeader
Design Arena: websites1243Not measuredOnly MiniMax M2.7 measured
Design Arena: UI components1210Not measuredOnly MiniMax M2.7 measured
Design Arena: game dev1210Not measuredOnly MiniMax M2.7 measured
Design Arena: data viz1233Not measuredOnly MiniMax M2.7 measured
Design Arena: 3D1195Not measuredOnly MiniMax M2.7 measured
Design Arena: all code categories1233Not measuredOnly MiniMax M2.7 measured
Design Arena: SVG1136Not measuredOnly MiniMax M2.7 measured
Design Arena: ASCII art1136Not measuredOnly MiniMax M2.7 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index712
General benchmarks for MiniMax M2.7 and Inkling Small
BenchmarkMiniMax M2.7Inkling SmallLeader
Vals IndexNot measured27.6%Only Inkling Small measured
Public Benefits Bench (Vals AI)Not measured59.4%Only Inkling Small measured
SAGE (Vals AI)Not measured32.7%Only Inkling Small measured
MedScribe (Vals AI)79.9%84.1%Inkling Small
Vals Multimodal IndexNot measured50.0%Only Inkling Small measured
IFBench75.7%Not measuredOnly MiniMax M2.7 measured
Long context reasoning (AA-LCR)78.3%75.7%MiniMax M2.7
ExploitBench13.3%Not measuredOnly MiniMax M2.7 measured
LMArena Text14051413Inkling Small
LMArena Text: instruction following14051399MiniMax M2.7
LMArena Text: creative writing13541334MiniMax M2.7
LMArena VisionNot measured1237Only Inkling Small measured
LMArena Text: English14261421MiniMax M2.7
LMArena Text: non-English13821401Inkling Small
LMArena Text: Chinese14421464Inkling Small
LMArena Text: German13981408Inkling Small
LMArena Text: Japanese12601401Inkling Small
LMArena Text: Korean13141367Inkling Small
LMArena Text: French14241435Inkling Small
LMArena Text: Spanish14021422Inkling Small
LMArena Text: Russian13831394Inkling Small
LMArena Text: Polish13871428Inkling Small
LMArena Text: multi-turn14121416Inkling Small
LMArena Text: longer queries14181402MiniMax M2.7
LMArena Text: writing and language13761357MiniMax M2.7
LMArena Text: entertainment and media13601352MiniMax M2.7
LMArena Vision: EnglishNot measured1243Only Inkling Small measured
LMArena Vision: ChineseNot measured1292Only Inkling Small measured
LMArena Vision: reading textNot measured1243Only Inkling Small measured
LMArena Vision: humorNot measured1207Only Inkling Small measured
LMArena Vision: creative writingNot measured1205Only Inkling Small measured
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2.7 and Inkling Small
BenchmarkMiniMax M2.7Inkling SmallLeader
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 M2.7$0.0009Fits in one request
Inkling Small$0.0010Fits in one request

MiniMax M2.7 costs less

Repository review

50K input + 3K output tokens

MiniMax M2.7$0.019Fits in one request
Inkling Small$0.026Fits in one request

MiniMax M2.7 costs less

Agent loop

200K input + 10K output tokens

MiniMax M2.7$0.072Exceeds the context window
Inkling Small$0.102Fits in one request

MiniMax M2.7 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 M2.7 and Inkling Small
SpecificationMiniMax M2.7Thinking Machines Inkling Small
MakerMiniMaxThinking Machines
WeightsOpen weightsOpen weights
ReleasedMarch 18, 2026July 30, 2026
Context window205K524K
Input $/Mtok$0.30$0.45
Output $/Mtok$1.20$1.20
Coding index28.429.9
Independent measurements behind it11
Cost per solved task$0.64$0.16
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2.7 better than Inkling Small for coding?

MiniMax M2.7 and Inkling Small are level for coding, 28.4 against 29.9 on the Vibe Coding Index, so price and context decide. Pick MiniMax M2.7 when what matters is SciCode or LMArena Text: coding, where it leads. Pick Inkling Small when a solved task costs $0.16 against $0.64, or when the context window is larger, 524K against 205K tokens.

Which is cheaper, MiniMax M2.7 or Inkling Small?

MiniMax M2.7 costs $0.30 per million input tokens and $1.20 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, MiniMax M2.7 costs $0.64 and Inkling Small $0.16.

Which has the bigger context window, MiniMax M2.7 or Inkling Small?

Inkling Small, with 524K tokens against 205K.

How many benchmarks is the MiniMax M2.7 vs Inkling Small comparison based on?

57 benchmarks have a result for both models as of October 21, 2026. MiniMax M2.7's coding index rests on 1 independent benchmark and Inkling Small's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next