LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Kimi K3 vs MiMo-V2.5-Pro

Updated October 21, 2026. 66 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Kimi K3 Replace MiMo-V2.5-Pro
Kimi K3Moonshot AI
Coding
61.8
Overall
43.6
Output $/M
$11.936
64
MiMo-V2.5-ProXiaomi
Coding
40.0
Overall
26.0
Output $/M
$0.609
2
vs boards won of 66 shared

Decision reading

Pick Kimi K3 for coding: it scores 61.8 on the Vibe Coding Index against 40.0 for MiMo-V2.5-Pro.

Pick MiMo-V2.5-Pro when output tokens cost 19.6x less, or when a solved task costs $0.03 against $0.81.

Model AKimi K3Moonshot AI61.8/1002 independent benchmarks$0.81 per solved taskModel BMiMo-V2.5-ProXiaomi40.0/1001 independent benchmark$0.03 per solved task
Shared results
66
Kimi K3 only
51
MiMo-V2.5-Pro only
4
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
Kimi K3 61.8 from 2 benchmarks, MiMo-V2.5-Pro 40.0 from 1 benchmark.
Widest category
Math, 23.2 points apart on average over 3 shared benchmarks.
Widest single gap
ProofBench: Kimi K3 87.0% against MiMo-V2.5-Pro 22.0%, 65.0 points apart on a 0 to 100 scale.
Output price
Kimi K3 $11.936 against MiMo-V2.5-Pro $0.609 per million output tokens, 19.6x apart.
Context window
Kimi K3 takes 1.05M tokens, MiMo-V2.5-Pro 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
CategoryKimi K3BarsMiMo-V2.5-ProTies
Coding131
Intelligence10
Agentic work50
Reasoning60
Math30
Knowledge90
Web design70
General201
All shared boards642
CodingLike-for-likeFour of these boards feed the Vibe Coding Index131
Coding benchmarks for Kimi K3 and MiMo-V2.5-Pro
BenchmarkKimi K3MiMo-V2.5-ProLeader
LiveBench coding59.3%Not measuredOnly Kimi K3 measured
LMArena WebDev16551480Kimi K3
AA Coding Index76.260.2Kimi K3
LiveCodeBench (Vals AI)87.2%81.3%Kimi K3
SWE-bench Verified (Vals AI)93.4%74.0%Kimi K3
Terminal-Bench 4 (Vals AI)17.2%0.5%Kimi K3
Vibe Code Bench (Vals AI)85.0%34.1%Kimi K3
Code migration (Vals AI)16.1%21.6%MiMo-V2.5-Pro
ProgramBench (Vals AI)2.0%Not measuredOnly Kimi K3 measured
IOI (Vals AI)48.9%Not measuredOnly Kimi K3 measured
Terminal-Bench 2.1 (Vals AI)80.9%57.3%Kimi K3
SWE-bench Multimodal (Vals AI)44.2%Not measuredOnly Kimi K3 measured
Vibe Code Bench 1-100 (Vals AI)18.2%Not measuredOnly Kimi K3 measured
CyberBench (Vals AI)75.2%Not measuredOnly Kimi K3 measured
SciCode59.5%50.6%Kimi K3
Terminal-Bench Hard (Artificial Analysis run)Not measured43.2%Only MiMo-V2.5-Pro measured
FrontierCode44.2%Not measuredOnly Kimi K3 measured
FrontierSWE25.9%Not measuredOnly Kimi K3 measured
WeirdML82.6%Not measuredOnly Kimi K3 measured
ALE-Bench1524.5899.8Kimi K3
LMArena Text: coding15081501Kimi K3
LMArena Text: software and IT14991495Kimi K3
LMArena WebDev: React16701469Kimi K3
LMArena WebDev: HTML16441473Kimi K3
LMArena WebDev: from an image1579Not measuredOnly Kimi K3 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Kimi K3 and MiMo-V2.5-Pro
BenchmarkKimi K3MiMo-V2.5-ProLeader
AA Intelligence Index43.626.0Kimi K3
Epoch Capabilities Index157.9Not measuredOnly Kimi K3 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
Agentic work benchmarks for Kimi K3 and MiMo-V2.5-Pro
BenchmarkKimi K3MiMo-V2.5-ProLeader
AA Agentic Index50.021.3Kimi K3
Design Arena: agents building web apps1296Not measuredOnly Kimi K3 measured
Design Arena: agents building full-stack apps1315Not measuredOnly Kimi K3 measured
Design Arena: agents building mobile apps1267Not measuredOnly Kimi K3 measured
Design Arena: agents building Android apps1256Not measuredOnly Kimi K3 measured
Design Arena: agents building Godot games1223Not measuredOnly Kimi K3 measured
Design Arena: agents building games1252Not measuredOnly Kimi K3 measured
Design Arena: HTML slides1256Not measuredOnly Kimi K3 measured
Design Arena: PowerPoint slides1273Not measuredOnly Kimi K3 measured
Design Arena: spreadsheets1058Not measuredOnly Kimi K3 measured
LiveBench research79.0%Not measuredOnly Kimi K3 measured
LiveBench browser16.0%Not measuredOnly Kimi K3 measured
LiveBench long agentic42.8%Not measuredOnly Kimi K3 measured
Finance Agent (Vals AI)53.1%41.5%Kimi K3
Tax Agent Bench (Vals AI)33.4%11.5%Kimi K3
Legal Research Bench (Vals AI)46.1%15.9%Kimi K3
Harvey's Legal Agent Benchmark (Vals AI)12.9%Not measuredOnly Kimi K3 measured
Excel Modeling Benchmark (Vals AI)66.7%55.2%Kimi K3
BioMysteryBench (Vals AI)72.6%Not measuredOnly Kimi K3 measured
Terminal-Bench-Science (Vals AI)1.4%Not measuredOnly Kimi K3 measured
Time Horizon Index (Vals AI)10.5%Not measuredOnly Kimi K3 measured
τ²-Bench TelecomNot measured94.2%Only MiMo-V2.5-Pro measured
APEX-Agents47.8%Not measuredOnly Kimi K3 measured
PostTrainBench32.0%Not measuredOnly Kimi K3 measured
Vending-Bench 2$5,165Not measuredOnly Kimi K3 measured
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for Kimi K3 and MiMo-V2.5-Pro
BenchmarkKimi K3MiMo-V2.5-ProLeader
GPQA Diamond92.9%82.6%Kimi K3
LiveBench reasoning90.7%Not measuredOnly Kimi K3 measured
MMMU Pro (Vals AI)88.2%Not measuredOnly Kimi K3 measured
GPQA Diamond (Artificial Analysis run)93.5%86.6%Kimi K3
Humanity's Last Exam (Artificial Analysis run)46.9%35.7%Kimi K3
GPQA Diamond (Epoch AI run)93.1%Not measuredOnly Kimi K3 measured
ARC-AGI94.5%Not measuredOnly Kimi K3 measured
ARC-AGI-260.4%Not measuredOnly Kimi K3 measured
SimpleBench60.7%Not measuredOnly Kimi K3 measured
Chess puzzles37.0%Not measuredOnly Kimi K3 measured
Mystery game puzzles26.0%Not measuredOnly Kimi K3 measured
LMArena Text: hard prompts14951486Kimi K3
LMArena Text: expert15201501Kimi K3
LMArena Text: hard prompts in English14961494Kimi K3
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for Kimi K3 and MiMo-V2.5-Pro
BenchmarkKimi K3MiMo-V2.5-ProLeader
OTIS Mock AIME97.2%Not measuredOnly Kimi K3 measured
FrontierMath, tiers 1 to 372.2%Not measuredOnly Kimi K3 measured
FrontierMath, tier 439.0%Not measuredOnly Kimi K3 measured
ProofBench87.0%22.0%Kimi K3
LMArena Text: math14941481Kimi K3
LMArena Text: mathematical work15051491Kimi K3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index90
Knowledge benchmarks for Kimi K3 and MiMo-V2.5-Pro
BenchmarkKimi K3MiMo-V2.5-ProLeader
MMLU Pro88.0%84.6%Kimi K3
LegalBench (Vals AI)86.2%77.1%Kimi K3
CorpFin (Vals AI)71.6%61.4%Kimi K3
TaxEval (Vals AI)75.7%73.8%Kimi K3
MortgageTax (Vals AI)66.3%Not measuredOnly Kimi K3 measured
MedCode (Vals AI)49.4%32.5%Kimi K3
SimpleQA Verified50.6%Not measuredOnly Kimi K3 measured
LMArena Text: science15081482Kimi K3
LMArena Text: medicine and healthcare14891473Kimi K3
LMArena Text: legal and government15031474Kimi K3
LMArena Text: business and finance14701466Kimi K3
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index70
Web design benchmarks for Kimi K3 and MiMo-V2.5-Pro
BenchmarkKimi K3MiMo-V2.5-ProLeader
Design Arena: websites13361267Kimi K3
Design Arena: UI components13451248Kimi K3
Design Arena: game dev13611261Kimi K3
Design Arena: data viz13501257Kimi K3
Design Arena: 3D13881244Kimi K3
Design Arena: all code categories13611266Kimi K3
Design Arena: SVG13011181Kimi K3
Design Arena: ASCII artNot measured1157Only MiMo-V2.5-Pro measured
LiveBench design77.2%Not measuredOnly Kimi K3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index201
General benchmarks for Kimi K3 and MiMo-V2.5-Pro
BenchmarkKimi K3MiMo-V2.5-ProLeader
Vals Index53.0%Not measuredOnly Kimi K3 measured
LiveBench data analysis78.7%Not measuredOnly Kimi K3 measured
Public Benefits Bench (Vals AI)68.2%Not measuredOnly Kimi K3 measured
SAGE (Vals AI)52.8%Not measuredOnly Kimi K3 measured
MedScribe (Vals AI)88.0%83.7%Kimi K3
Vals Multimodal Index73.4%Not measuredOnly Kimi K3 measured
IFBenchNot measured79.9%Only MiMo-V2.5-Pro measured
Long context reasoning (AA-LCR)88.7%79.7%Kimi K3
DTBench91.2%84.5%Kimi K3
LMCA52.7%29.5%Kimi K3
Surface Evolver Bench95.0%Not measuredOnly Kimi K3 measured
Furniture assembly34.2%Not measuredOnly Kimi K3 measured
LMArena Text14761464Kimi K3
LMArena Text: instruction following14851475Kimi K3
LMArena Text: creative writing14571438Kimi K3
LMArena Text: English14811477Kimi K3
LMArena Text: non-English14661448Kimi K3
LMArena Text: Chinese15291507Kimi K3
LMArena Text: German14901459Kimi K3
LMArena Text: Japanese14941410Kimi K3
LMArena Text: Korean14601435Kimi K3
LMArena Text: French14921487Kimi K3
LMArena Text: Spanish14721469Kimi K3
LMArena Text: Russian14851449Kimi K3
LMArena Text: Polish14581464MiMo-V2.5-Pro
LMArena Text: multi-turn14891476Kimi K3
LMArena Text: longer queries14941481Kimi K3
LMArena Text: writing and language14711451Kimi K3
LMArena Text: entertainment and media14531438Kimi K3
Neither model has a result on the other 17 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Kimi K3 and MiMo-V2.5-Pro
BenchmarkKimi K3MiMo-V2.5-ProLeader
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

Kimi K3$0.0062Fits in one request
MiMo-V2.5-Pro$0.0006Fits in one request

MiMo-V2.5-Pro costs less

Repository review

50K input + 3K output tokens

Kimi K3$0.048Fits in one request
MiMo-V2.5-Pro$0.017Fits in one request

MiMo-V2.5-Pro costs less

Agent loop

200K input + 10K output tokens

Kimi K3$0.167Fits in one request
MiMo-V2.5-Pro$0.067Fits in one request

MiMo-V2.5-Pro 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 Kimi K3 and MiMo-V2.5-Pro
SpecificationMoonshotAI Kimi K3Xiaomi MiMo-V2.5-Pro
MakerMoonshot AIXiaomi
WeightsOpen weightsOpen weights
ReleasedJuly 16, 2026April 22, 2026
Context window1.05M1.05M
Input $/Mtok$0.239$0.3045
Output $/Mtok$11.936$0.609
Coding index61.840.0
Independent measurements behind it21
Cost per solved task$0.81$0.03
SourceOpenRouter listingOpenRouter listing

Questions

Is Kimi K3 better than MiMo-V2.5-Pro for coding?

Pick Kimi K3 for coding: it scores 61.8 on the Vibe Coding Index against 40.0 for MiMo-V2.5-Pro. Pick MiMo-V2.5-Pro when output tokens cost 19.6x less, or when a solved task costs $0.03 against $0.81.

Which is cheaper, Kimi K3 or MiMo-V2.5-Pro?

Kimi K3 costs $0.239 per million input tokens and $11.936 per million output tokens; MiMo-V2.5-Pro costs $0.3045 and $0.609. Per solved SWE-bench Verified task, Kimi K3 costs $0.81 and MiMo-V2.5-Pro $0.03.

Which has the bigger context window, Kimi K3 or MiMo-V2.5-Pro?

MiMo-V2.5-Pro, with 1.05M tokens against 1.05M.

How many benchmarks is the Kimi K3 vs MiMo-V2.5-Pro comparison based on?

66 benchmarks have a result for both models as of October 21, 2026. Kimi K3's coding index rests on 2 independent benchmarks and MiMo-V2.5-Pro's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next