Enter opens the highlighted result. Esc closes.

Inkling 2 Mini vs MiMo-V2.5

MiMo-V2.5 leads Inkling 2 Mini on coding, 50.0 to 39.5 on the Vibe Coding Index, and Inkling 2 Mini costs 6.2x less per output token ($0.325 vs $2.00 per million). Updated November 22, 2026; 10 benchmarks have a result for both.

T Inkling 2 MiniThinking Machines
Coding
39.5
Overall
No data
Output $/M
$0.325
9
MiMo-V2.5Xiaomi
Coding
50.0
Overall
No data
Output $/M
$2.00
1
vs boards won of 10 shared

Inkling 2 Mini or MiMo-V2.5: which to pick

Pick MiMo-V2.5 for coding: it scores 50.0 on the Vibe Coding Index against 39.5 for Inkling 2 Mini.

Pick Inkling 2 Mini for output tokens 6.2x cheaper ($0.325 vs $2.00 per million) and a larger context window (1.05M against 1M tokens).

Shared results
10
Inkling 2 Mini only
19
MiMo-V2.5 only
70
Like-for-like categories
5 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
Inkling 2 Mini 39.5 from 2 benchmarks, MiMo-V2.5 50.0 from 3 benchmarks.
Widest category
Coding, 20.7 points apart on average over 2 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Inkling 2 Mini 77.9% against MiMo-V2.5 42.2%, 35.8 points apart on a 0 to 100 scale.
Output price
Inkling 2 Mini $0.325 against MiMo-V2.5 $2.00 per million output tokens, 6.2x apart.
Context window
Inkling 2 Mini takes 1.05M tokens, MiMo-V2.5 1M.

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
CategoryInkling 2 MiniBarsMiMo-V2.5Ties
Coding20
Agentic work20
Knowledge01
Web design30
General20
All shared boards91
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
Coding benchmarks for Inkling 2 Mini and MiMo-V2.5
BenchmarkInkling 2 MiniMiMo-V2.5Leader
LMArena WebDevNot measured1438Only MiMo-V2.5 measured
LiveCodeBench (Vals AI)Not measured81.5%Only MiMo-V2.5 measured
SWE-bench Verified (Vals AI)Not measured71.0%Only MiMo-V2.5 measured
Terminal-Bench 4 (Vals AI)6.6%Not measuredOnly Inkling 2 Mini measured
Vibe Code Bench (Vals AI)77.9%42.2%Inkling 2 Mini
Code migration (Vals AI)Not measured14.2%Only MiMo-V2.5 measured
ProgramBench (Vals AI)0.5%Not measuredOnly Inkling 2 Mini measured
IOI (Vals AI)11.6%Not measuredOnly Inkling 2 Mini measured
Terminal-Bench 2.1 (Vals AI)Not measured60.7%Only MiMo-V2.5 measured
SWE-bench Multimodal (Vals AI)37.9%Not measuredOnly Inkling 2 Mini measured
SkillsBench (Vals AI)43.2%Not measuredOnly Inkling 2 Mini measured
CyberBench (Vals AI)74.6%Not measuredOnly Inkling 2 Mini measured
SciCodeNot measured43.9%Only MiMo-V2.5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured41.7%Only MiMo-V2.5 measured
Terminal-Bench 4.0 (Artificial Analysis run)5.6%0.0%Inkling 2 Mini
FrontierCode 2.015.1%Not measuredOnly Inkling 2 Mini measured
ALE-BenchNot measured514.0Only MiMo-V2.5 measured
LMArena Text: codingNot measured1469Only MiMo-V2.5 measured
LMArena Text: software and ITNot measured1464Only MiMo-V2.5 measured
LMArena WebDev: ReactNot measured1423Only MiMo-V2.5 measured
LMArena WebDev: HTMLNot measured1428Only MiMo-V2.5 measured
GameBench 2Not measured24.0Only MiMo-V2.5 measured
Neither model has a result on the other 30 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Intelligence benchmarks for Inkling 2 Mini and MiMo-V2.5
BenchmarkInkling 2 MiniMiMo-V2.5Leader
AA Intelligence Index20.1Not measuredOnly Inkling 2 Mini measured
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Inkling 2 Mini and MiMo-V2.5
BenchmarkInkling 2 MiniMiMo-V2.5Leader
SREBench (Vals AI)0.0%Not measuredOnly Inkling 2 Mini measured
Finance Agent (Vals AI)Not measured36.7%Only MiMo-V2.5 measured
Tax Agent Bench (Vals AI)14.1%7.8%Inkling 2 Mini
Legal Research Bench (Vals AI)17.8%9.1%Inkling 2 Mini
Harvey's Legal Agent Benchmark (Vals AI)5.0%Not measuredOnly Inkling 2 Mini measured
Excel Modeling Benchmark (Vals AI)Not measured55.1%Only MiMo-V2.5 measured
BioMysteryBench (Vals AI)47.8%Not measuredOnly Inkling 2 Mini measured
Terminal-Bench-Science (Vals AI)0.0%Not measuredOnly Inkling 2 Mini measured
Vals Science Index23.6%Not measuredOnly Inkling 2 Mini measured
τ²-Bench TelecomNot measured90.6%Only MiMo-V2.5 measured
Toolathlon-VerifiedNot measured49.1%Only MiMo-V2.5 measured
Neither model has a result on the other 33 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
Reasoning benchmarks for Inkling 2 Mini and MiMo-V2.5
BenchmarkInkling 2 MiniMiMo-V2.5Leader
GPQA DiamondNot measured81.6%Only MiMo-V2.5 measured
MysteryMechanism (Vals AI)23.0%Not measuredOnly Inkling 2 Mini measured
MMMU Pro (Vals AI)Not measured80.0%Only MiMo-V2.5 measured
GPQA Diamond (Artificial Analysis run)Not measured84.9%Only MiMo-V2.5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured27.2%Only MiMo-V2.5 measured
HLE-Diamond (Artificial Analysis run)15.2%Not measuredOnly Inkling 2 Mini measured
CritPt v2, hard subset (Artificial Analysis run)17.0%Not measuredOnly Inkling 2 Mini measured
LMArena Text: hard promptsNot measured1450Only MiMo-V2.5 measured
LMArena Text: expertNot measured1459Only MiMo-V2.5 measured
LMArena Text: hard prompts in EnglishNot measured1461Only MiMo-V2.5 measured
LMArena Vision: diagramsNot measured1270Only MiMo-V2.5 measured
LMArena Vision: homeworkNot measured1261Only MiMo-V2.5 measured
Neither model has a result on the other 14 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Math benchmarks for Inkling 2 Mini and MiMo-V2.5
BenchmarkInkling 2 MiniMiMo-V2.5Leader
ProofBenchNot measured16.0%Only MiMo-V2.5 measured
LMArena Text: mathNot measured1435Only MiMo-V2.5 measured
LMArena Text: mathematical workNot measured1449Only MiMo-V2.5 measured
Neither model has a result on the other 11 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
Knowledge benchmarks for Inkling 2 Mini and MiMo-V2.5
BenchmarkInkling 2 MiniMiMo-V2.5Leader
MMLU ProNot measured82.9%Only MiMo-V2.5 measured
LegalBench (Vals AI)Not measured78.9%Only MiMo-V2.5 measured
CorpFin (Vals AI)Not measured59.9%Only MiMo-V2.5 measured
TaxEval (Vals AI)Not measured71.8%Only MiMo-V2.5 measured
MortgageTax (Vals AI)Not measured59.3%Only MiMo-V2.5 measured
MedCode (Vals AI)25.7%31.9%MiMo-V2.5
AA-Omniscience-8.6Not measuredOnly Inkling 2 Mini measured
LMArena Text: scienceNot measured1439Only MiMo-V2.5 measured
LMArena Text: medicine and healthcareNot measured1432Only MiMo-V2.5 measured
LMArena Text: legal and governmentNot measured1424Only MiMo-V2.5 measured
LMArena Text: business and financeNot measured1432Only MiMo-V2.5 measured
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index30
Web design benchmarks for Inkling 2 Mini and MiMo-V2.5
BenchmarkInkling 2 MiniMiMo-V2.5Leader
Design Arena: websitesNot measured1255Only MiMo-V2.5 measured
Design Arena: UI components12921242Inkling 2 Mini
Design Arena: game dev12871225Inkling 2 Mini
Design Arena: data vizNot measured1246Only MiMo-V2.5 measured
Design Arena: 3D13081185Inkling 2 Mini
Design Arena: all code categoriesNot measured1244Only MiMo-V2.5 measured
Design Arena: SVGNot measured1173Only MiMo-V2.5 measured
Design Arena: ASCII artNot measured1128Only MiMo-V2.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
General benchmarks for Inkling 2 Mini and MiMo-V2.5
BenchmarkInkling 2 MiniMiMo-V2.5Leader
Vals Index46.5%Not measuredOnly Inkling 2 Mini measured
SAGE (Vals AI)85.9%Not measuredOnly Inkling 2 Mini measured
MedScribe (Vals AI)86.4%72.2%Inkling 2 Mini
Vals Multimodal IndexNot measured52.8%Only MiMo-V2.5 measured
IFBenchNot measured67.1%Only MiMo-V2.5 measured
Long context reasoning (AA-LCR)Not measured73.0%Only MiMo-V2.5 measured
GDPval-AA13191004Inkling 2 Mini
LMArena TextNot measured1428Only MiMo-V2.5 measured
LMArena Text: instruction followingNot measured1434Only MiMo-V2.5 measured
LMArena Text: creative writingNot measured1391Only MiMo-V2.5 measured
LMArena VisionNot measured1247Only MiMo-V2.5 measured
LMArena Text: EnglishNot measured1447Only MiMo-V2.5 measured
LMArena Text: non-EnglishNot measured1404Only MiMo-V2.5 measured
LMArena Text: ChineseNot measured1471Only MiMo-V2.5 measured
LMArena Text: GermanNot measured1419Only MiMo-V2.5 measured
LMArena Text: JapaneseNot measured1307Only MiMo-V2.5 measured
LMArena Text: KoreanNot measured1356Only MiMo-V2.5 measured
LMArena Text: FrenchNot measured1450Only MiMo-V2.5 measured
LMArena Text: SpanishNot measured1416Only MiMo-V2.5 measured
LMArena Text: RussianNot measured1395Only MiMo-V2.5 measured
LMArena Text: PolishNot measured1410Only MiMo-V2.5 measured
LMArena Text: multi-turnNot measured1445Only MiMo-V2.5 measured
LMArena Text: longer queriesNot measured1445Only MiMo-V2.5 measured
LMArena Text: writing and languageNot measured1408Only MiMo-V2.5 measured
LMArena Text: entertainment and mediaNot measured1399Only MiMo-V2.5 measured
LMArena Vision: EnglishNot measured1260Only MiMo-V2.5 measured
LMArena Vision: ChineseNot measured1322Only MiMo-V2.5 measured
LMArena Vision: reading textNot measured1256Only MiMo-V2.5 measured
LMArena Vision: humorNot measured1227Only MiMo-V2.5 measured
LMArena Vision: recognizing thingsNot measured1195Only MiMo-V2.5 measured
LMArena Vision: creative writingNot measured1230Only MiMo-V2.5 measured
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Inkling 2 Mini and MiMo-V2.5
BenchmarkInkling 2 MiniMiMo-V2.5Leader
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

Inkling 2 Mini$0.0002Fits in one request
MiMo-V2.5$0.0014Fits in one request

Inkling 2 Mini costs less

Repository review

50K input + 3K output tokens

Inkling 2 Mini$0.0049Fits in one request
MiMo-V2.5$0.026Fits in one request

Inkling 2 Mini costs less

Agent loop

200K input + 10K output tokens

Inkling 2 Mini$0.019Fits in one request
MiMo-V2.5$0.100Fits in one request

Inkling 2 Mini 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 Inkling 2 Mini and MiMo-V2.5
SpecificationThinking Machines Inkling 2 MiniXiaomi MiMo-V2.5
MakerThinking MachinesXiaomi
WeightsOpen weightsOpen weights
ReleasedNovember 21, 2026April 22, 2026
Context window1.05M1M
Input $/Mtok$0.0775$0.40
Output $/Mtok$0.325$2.00
Coding index39.550.0
Independent measurements behind it23
Cost per solved taskNot computable$0.01
SourceOpenRouter listingOpenRouter listing

Questions

Is Inkling 2 Mini better than MiMo-V2.5 for coding?

Pick MiMo-V2.5 for coding: it scores 50.0 on the Vibe Coding Index against 39.5 for Inkling 2 Mini. Pick Inkling 2 Mini for output tokens 6.2x cheaper ($0.325 vs $2.00 per million) and a larger context window (1.05M against 1M tokens).

Which is cheaper, Inkling 2 Mini or MiMo-V2.5?

Inkling 2 Mini costs $0.0775 per million input tokens and $0.325 per million output tokens; MiMo-V2.5 costs $0.40 and $2.00. Cost per solved task is known for MiMo-V2.5 only.

Which has the bigger context window, Inkling 2 Mini or MiMo-V2.5?

Inkling 2 Mini, with 1.05M tokens against 1M.

How many benchmarks is the Inkling 2 Mini vs MiMo-V2.5 comparison based on?

10 benchmarks have a result for both models as of November 22, 2026. Inkling 2 Mini's coding index rests on 2 independent benchmarks and MiMo-V2.5's on 3. 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/thinkingmachines-inkling-2-mini-vs-xiaomi-mimo-v2-5" title="Inkling 2 Mini vs MiMo-V2.5, 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/thinkingmachines-inkling-2-mini-vs-xiaomi-mimo-v2-5">LLMBenchmark.ai, Inkling 2 Mini vs MiMo-V2.5</a></p>