llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1450 models809 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Moonshot AI model product

Kimi K2.5

5 is an open large language model from Moonshot AI that combines vision and text with thinking and non-thinking modes.

Updated Nov 18, 2026. Default version: Kimi K2.5

LLMBoard Score63.8Kimi K2.5
Coverage100%38 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Kimi K2.5 Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Kimi K2.5 LLMBoard score breakdown

Kimi K2.5 Benchmark Results

Benchmark scores for Kimi K2.5.

30 of 54 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkFinSearchComp T2&T3Score67.80%Rank01Participants1Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkInfoVQAtestScore92.60%Rank01Participants12Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkMathVista-MiniScore90.10%Rank01Participants27Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkOCRBenchScore92.30%Rank01Participants25Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkOJBench (C++)Score57.40%Rank01Participants1Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkSeal-0Score57.40%Rank01Participants7Percentile100.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkMMVUScore80.40%Rank02Participants8Percentile85.71%EvidenceCEvaluatedNov 17, 2026
BenchmarkLongVideoBenchScore79.80%Rank03Participants6Percentile60.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkPaperBenchScore63.50%Rank03Participants4Percentile33.33%EvidenceCEvaluatedNov 17, 2026
BenchmarkVideoMMMUScore86.60%Rank03Participants29Percentile92.86%EvidenceCEvaluatedNov 17, 2026
BenchmarkMotionBenchScore70.40%Rank04Participants6Percentile40.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkVideo-MMEScore87.40%Rank05Participants18Percentile76.47%EvidenceCEvaluatedNov 17, 2026
BenchmarkWideSearchScore79.00%Rank05Participants15Percentile71.43%EvidenceCEvaluatedNov 17, 2026
BenchmarkHMMT 2025Score95.40%Rank06Participants33Percentile84.38%EvidenceCEvaluatedNov 17, 2026
BenchmarkLongBench v2Score61.00%Rank07Participants19Percentile66.67%EvidenceCEvaluatedNov 17, 2026
BenchmarkSimpleVQAScore0.71 pointsRank07Participants18Percentile64.71%EvidenceCEvaluatedNov 17, 2026
BenchmarkWorldVQAScore46.30%Rank07Participants7Percentile0.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkMMLU-ProScore87.10%Rank08Participants142Percentile95.04%EvidenceCEvaluatedNov 17, 2026
BenchmarkAA-LCRScore70.00%Rank10Participants32Percentile70.97%EvidenceCEvaluatedNov 17, 2026
BenchmarkDeepSearchQAScore77.10%Rank10Participants13Percentile25.00%EvidenceCEvaluatedNov 17, 2026
BenchmarkLVBenchScore75.90%Rank10Participants32Percentile70.97%EvidenceCEvaluatedNov 17, 2026
BenchmarkOmniDocBench 1.5Score88.80%Rank10Participants20Percentile52.63%EvidenceCEvaluatedNov 17, 2026
BenchmarkSciCodeScore48.70%Rank11Participants37Percentile72.22%EvidenceCEvaluatedNov 17, 2026
BenchmarkZEROBenchScore0.11 pointsRank11Participants17Percentile37.50%EvidenceCEvaluatedNov 17, 2026
BenchmarkMathVisionScore84.20%Rank14Participants40Percentile66.67%EvidenceCEvaluatedNov 17, 2026
BenchmarkLiveCodeBench v6Score85.00%Rank15Participants69Percentile79.41%EvidenceCEvaluatedNov 17, 2026
BenchmarkFrontierSWEScore26.00%Rank16Participants17Percentile6.25%EvidenceBEvaluatedNov 17, 2026
BenchmarkIMO-AnswerBenchScore81.80%Rank16Participants22Percentile28.57%EvidenceCEvaluatedNov 17, 2026
BenchmarkAIME 2025Score96.10%Rank19Participants123Percentile85.25%EvidenceCEvaluatedNov 17, 2026
BenchmarkMMMU-ProScore78.50%Rank21Participants77Percentile73.68%EvidenceCEvaluatedNov 17, 2026

Kimi K2.5 Arena Results

Preference and agent-evaluation results for the default version.

30 of 100 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenavisionCategoryentity recognitionRank06Rating / score1,287.14Votes274ObservationsN/AResult dateNov 9, 2026
Arenavision style controlCategoryentity recognitionRank11Rating / score1,234.17Votes274ObservationsN/AResult dateNov 9, 2026
ArenavisionCategorycaptioningRank12Rating / score1,250.22Votes119ObservationsN/AResult dateNov 9, 2026
Arenavision style controlCategorycaptioningRank15Rating / score1,192.63Votes119ObservationsN/AResult dateNov 9, 2026
Arenatext factualityCategorykoreanRank17Rating / score1,415.17Votes726ObservationsN/AResult dateNov 11, 2026
ArenavisionCategoryhumorRank19Rating / score1,284.26Votes1,071ObservationsN/AResult dateNov 9, 2026
Arenatext factualityCategoryjapaneseRank26Rating / score1,421.89Votes543ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorygermanRank27Rating / score1,414.01Votes747ObservationsN/AResult dateNov 11, 2026
Arenavision style controlCategoryhumorRank27Rating / score1,262.68Votes1,071ObservationsN/AResult dateNov 9, 2026
ArenavisionCategorycreative writing visionRank28Rating / score1,270.36Votes1,752ObservationsN/AResult dateNov 9, 2026
ArenavisionCategoryhomeworkRank30Rating / score1,295.82Votes3,597ObservationsN/AResult dateNov 9, 2026
ArenavisionCategorychineseRank31Rating / score1,327.30Votes271ObservationsN/AResult dateNov 9, 2026
Arenavision style controlCategorychineseRank31Rating / score1,307.17Votes271ObservationsN/AResult dateNov 9, 2026
ArenadocumentCategoryoverallRank32Rating / score1,430.68Votes22,601ObservationsN/AResult dateNov 9, 2026
ArenavisionCategoryenglishRank32Rating / score1,274.14Votes10,879ObservationsN/AResult dateNov 9, 2026
Arenadocument style controlCategoryoverallRank33Rating / score1,437.55Votes22,601ObservationsN/AResult dateNov 9, 2026
Arenavision style controlCategoryhomeworkRank33Rating / score1,289.10Votes3,597ObservationsN/AResult dateNov 9, 2026
ArenavisionCategoryoverallRank35Rating / score1,268.85Votes28,014ObservationsN/AResult dateNov 9, 2026
Arenavision style controlCategorycreative writing visionRank35Rating / score1,248.31Votes1,752ObservationsN/AResult dateNov 9, 2026
Arenatext factualityCategorycodingRank36Rating / score1,516.52Votes982ObservationsN/AResult dateNov 11, 2026
ArenavisionCategoryocrRank36Rating / score1,275.75Votes19,325ObservationsN/AResult dateNov 9, 2026
ArenatextCategorymathRank37Rating / score1,468.78Votes4,120ObservationsN/AResult dateNov 11, 2026
Arenatext factualityCategorypolishRank37Rating / score1,423.26Votes994ObservationsN/AResult dateNov 11, 2026
ArenavisionCategorydiagramRank37Rating / score1,282.23Votes7,332ObservationsN/AResult dateNov 9, 2026
Arenavision style controlCategoryocrRank37Rating / score1,265.94Votes19,325ObservationsN/AResult dateNov 9, 2026
ArenatextCategorycodingRank38Rating / score1,484.21Votes1,863ObservationsN/AResult dateNov 11, 2026
Arenavision style controlCategoryoverallRank38Rating / score1,252.09Votes28,014ObservationsN/AResult dateNov 9, 2026
ArenatextCategoryindustry mathematicalRank39Rating / score1,472.54Votes3,962ObservationsN/AResult dateNov 11, 2026
Arenavision style controlCategorydiagramRank39Rating / score1,279.90Votes7,332ObservationsN/AResult dateNov 9, 2026
Arenavision style controlCategoryenglishRank39Rating / score1,254.80Votes10,879ObservationsN/AResult dateNov 9, 2026

Kimi K2.5 Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.45 input, $2.25 output per 1M via Meganova
Tracked offerings
40
30 of 40 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderAlibaba Token PlanProvider model IDkimi-k2.5RegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedNov 18, 2026
ProviderAlibaba Coding Plan (China)Provider model IDkimi-k2.5RegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedNov 18, 2026
ProviderAlibaba Coding PlanProvider model IDkimi-k2.5RegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedNov 18, 2026
ProviderTencent Coding Plan (China)Provider model IDkimi-k2.5RegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedNov 18, 2026
ProviderSCNet Token PlanProvider model IDKimi-K2.5RegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedNov 18, 2026
ProviderAlibaba Token Plan (China)Provider model IDkimi-k2.5RegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedNov 18, 2026
ProviderMeganovaProvider model IDmoonshotai/Kimi-K2.5RegionglobalInput / 1M$0.45Output / 1M$2.25Context262.1KUpdatedNov 18, 2026
ProviderDeep InfraProvider model IDmoonshotai/Kimi-K2.5RegionglobalInput / 1M$0.45Output / 1M$2.25Context262.1KUpdatedNov 18, 2026
ProviderAurikoProvider model IDkimi-k2.5RegionglobalInput / 1M$0.45Output / 1M$2.25Context262.1KUpdatedNov 18, 2026
ProviderSiliconFlowProvider model IDmoonshotai/Kimi-K2.5RegionglobalInput / 1M$0.45Output / 1M$2.25Context262KUpdatedNov 18, 2026
ProviderOpenRouterProvider model IDmoonshotai/kimi-k2.5RegionglobalInput / 1M$0.50Output / 1M$2.5Context262.1KUpdatedNov 18, 2026
ProviderTensorXProvider model IDmoonshotai/kimi-k2.5RegionglobalInput / 1M$0.50Output / 1M$2.8Context262.1KUpdatedNov 18, 2026
ProviderIteraComputeProvider model IDmoonshotai/kimi-k2.5RegionglobalInput / 1M$0.54Output / 1M$2.78Context262.1KUpdatedNov 18, 2026
ProviderZenifraProvider model IDzenifra/kimi-k2.5RegionglobalInput / 1M$0.544Output / 1M$2.85Context229.4KUpdatedNov 18, 2026
ProviderNanoGPTProvider model IDmoonshotai/kimi-k2.5RegionglobalInput / 1M$0.557Output / 1M$2.83Context262.1KUpdatedNov 18, 2026
ProviderVenice AIProvider model IDkimi-k2-5RegionglobalInput / 1M$0.56Output / 1M$3.5Context256KUpdatedNov 18, 2026
ProviderAlibaba (China)Provider model IDkimi-k2.5RegionglobalInput / 1M$0.574Output / 1M$3.01Context262.1KUpdatedNov 18, 2026
ProviderDevPass (LLM Gateway)Provider model IDkimi-k2.5RegionglobalInput / 1M$0.574Output / 1M$3.01Context262.1KUpdatedNov 18, 2026
ProviderQiniuProvider model IDmoonshotai/kimi-k2.5RegionglobalInput / 1M$0.5797Output / 1M$3.04Context256KUpdatedNov 18, 2026
ProviderHPC-AIProvider model IDmoonshotai/kimi-k2.5RegionglobalInput / 1M$0.60Output / 1M$3Context256KUpdatedNov 18, 2026
ProviderOrcaRouterProvider model IDkimi/kimi-k2.5RegionglobalInput / 1M$0.60Output / 1M$3Context262.1KUpdatedNov 18, 2026
ProviderJalapeno CloudProvider model IDKimi-K2.5RegionglobalInput / 1M$0.60Output / 1M$3Context262.1KUpdatedNov 18, 2026
ProviderHugging FaceProvider model IDmoonshotai/Kimi-K2.5RegionglobalInput / 1M$0.60Output / 1M$3Context262.1KUpdatedNov 18, 2026
ProviderJiekou.AIProvider model IDmoonshotai/kimi-k2.5RegionglobalInput / 1M$0.60Output / 1M$3Context262.1KUpdatedNov 18, 2026
ProviderAmazon BedrockProvider model IDmoonshotai.kimi-k2.5RegionglobalInput / 1M$0.60Output / 1M$3Context262.1KUpdatedNov 18, 2026
ProviderMerge GatewayProvider model IDmoonshot/kimi-k2.5RegionglobalInput / 1M$0.60Output / 1M$3Context262.1KUpdatedNov 18, 2026
ProviderAzure Cognitive ServicesProvider model IDkimi-k2.5RegionglobalInput / 1M$0.60Output / 1M$3Context262.1KUpdatedNov 18, 2026
ProviderOpenCodeProvider model IDkimi-k2.5RegionglobalInput / 1M$0.60Output / 1M$3Context262.1KUpdatedNov 18, 2026
ProviderAzureProvider model IDkimi-k2.5RegionglobalInput / 1M$0.60Output / 1M$3Context262.1KUpdatedNov 18, 2026
ProviderFrogBotProvider model IDkimi-k2.5RegionglobalInput / 1M$0.60Output / 1M$3Context256KUpdatedNov 18, 2026

Kimi K2.5 Runtime Performance

Provider-specific output speed and catalog latency for Kimi K2.5. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Kimi K2.5 Specifications

Technical details for the model's default version.

Version
Kimi K2.5
Released
Jan 27, 2026
Knowledge cutoff
Unknown
Parameters
1T
Context window
262.1K
Max output
262.1K
Inputs
image, text, video
Outputs
text
Open weights
Yes
License
MIT

Kimi K2.5 Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionKimi K2.5ReleasedJan 27, 2026LLMBoard63.78Parameters1TContext262.1KMax output262.1KOpen weightsYesLicenseMIT

Models similar to Kimi K2.5

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#100-1.67
MA

Kimi K2.7 Code

Moonshot AI

62.11 LLMBoard

Details
#111-5.50
MA

Kimi K2 Thinking

Moonshot AI

58.28 LLMBoard

Details
#59+8.31
MA

Kimi K2.6

Moonshot AI

72.09 LLMBoard

Details
#17+19.32
MA

Kimi K3

Moonshot AI

83.10 LLMBoard

Details
#10+23.27
MA

Kimi K3.1 Pro

Moonshot AI

87.05 LLMBoard

Details
#215-28.89
MA

Kimi K2

Moonshot AI

34.89 LLMBoard

Details

What is Kimi K2.5?

Key information about Kimi K2.5 and its available data.

5 is Moonshot AI's flagship agentic model, supporting vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution. It uses Full-Parameter RL tuning and is evaluated across agent, coding, image, and video benchmarks.

Data as of 2026-11-17.

FAQ

Common questions about Kimi K2.5.

When was Kimi K2.5 released?

Kimi K2.5's default version was released on Jan 27, 2026.

How much does Kimi K2.5 cost?

No official standard PAYG price is currently available for Kimi K2.5. The lowest tracked third-party offer starts at $0.45 input and $2.25 output via Meganova.

Who created Kimi K2.5?

Kimi K2.5 was created by Moonshot AI.

What is the context window for Kimi K2.5?

The default version has a 262.1K token context window.

Is Kimi K2.5 open weight?

Yes. The default version is marked as open weight under MIT.

How many API providers offer Kimi K2.5?

40 provider offerings are linked to the default version.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Browse runtime rankings