Skip to main content

Model profile

Kimi K2.7 Code

Moonshot AICurrentReleased Jun 12, 2026
Data verified
Overall Score
55Public #87 of 200
Arena Elo
Not listed
Eligible category ranks
2of 8
Price (1M tokens)
$0.95 in / $4 out
API pricing
Speed
Not listed
Context
256K

Evidence coverage

23 of 323 tracked benchmarks are published. 7 are verified and 16 provisional. 6 of 8 categories are measured.

Updated July 23, 2026Methodology
Published / tracked
23 / 323
Verified
7
Provisional
16
Categories with evidence
6 / 8

Evidence by category

  • Agentic7 benchmarks
    Mixed evidence
  • Coding6 benchmarks
    Mixed evidence
  • Reasoning2 benchmarks
    Reported
  • Knowledge6 benchmarks
    Reported
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal1 benchmark
    Reported
  • Inst. Following1 benchmark
    Reported
Open WeightSelf-hostReasoning
Confidence:
Low
code

Kimi K2.7 Code ranks #87 out of 200 models on the public leaderboard with an overall score of 55/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Kimi K2.7 Code is a open weight model with a 256K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

BenchLM links it directly to Kimi K2.6 as the earlier related model in that lineage. This profile currently has 23 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Coding (#38), while its weakest is Agentic (#99). This performance profile makes it particularly well-suited for software development and code generation tasks.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 54.6855.4

  1. DeepSeek V3.2
    DeepSeek
    #8255.4
    DeepSeek V3.2 is #82 with a score of 55.4.
    Compare
  2. Gemini 3.1 Pro
    Google
    #8355.3
    Gemini 3.1 Pro is #83 with a score of 55.3.
    Compare
  3. GPT-5 (medium)
    OpenAI
    #8455.15
    GPT-5 (medium) is #84 with a score of 55.15.
    Compare
  4. GLM-4.6
    Z.AI
    #8555.12
    GLM-4.6 is #85 with a score of 55.12.
    Compare
  5. Step 3.5 Flash
    StepFun
    #8655.1
    Step 3.5 Flash is #86 with a score of 55.1.
    Compare
  6. Kimi K2.7 CodeCurrent model
    Moonshot AI
    #8755.0
    Kimi K2.7 Code is #87 with a score of 55.0.
  7. Grok 4.20
    xAI
    #8854.68
    Grok 4.20 is #88 with a score of 54.68.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Coding69%
    Eligible cohort rank #38 of 122Category score 54.2
  2. Agentic17%
    Eligible cohort rank #99 of 119Category score 38.0

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #99 of 119Percentile 17thWeight 22%7 benchmarksMixed sources38.0
CodingRank #38 of 122Percentile 69thWeight 20%6 benchmarksMixed sources54.2
ReasoningWeight 17%2 benchmarksReportedScore pending
KnowledgeWeight 12%6 benchmarksReportedScore pending
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%1 benchmarkReportedScore pending
Inst. FollowingWeight 5%1 benchmarkReportedScore pending

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Kimi K2.7 Code
API / mo$3,713
Self-host / mo$18,221
Break-even326M/day
Model the full break-even

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic7 benchmarks
Kimi Claw 24/7Provider exact

Kimi Claw 24/7 Bench

46.9%Display only
Source: MoonshotAI: Kimi K2.7 Code model cardProvenance: MoonshotAI reports Kimi Claw 24/7 Bench at 46.9 for Kimi K2.7 Code. BenchLM treats this provider-run internal benchmark as display-only launch evidence.
MCP AtlasProvider exact
76%Display only
Source: MoonshotAI: Kimi K2.7 Code model cardProvenance: MoonshotAI reports MCP Atlas at 76.0 for Kimi K2.7 Code using the official MCP-Atlas evaluation configuration.
MCP Mark VerifiedProvider exact

MCPMark-Verified

81.1%Display only
Source: MoonshotAI: Kimi K2.7 Code model cardProvenance: MoonshotAI reports MCP Mark Verified at 81.1 for Kimi K2.7 Code. BenchLM treats this human-verified MCPMark variant as display-only launch evidence until a stable public source is available.
AA Agentic IndexReported

Artificial Analysis Agentic Index

29.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

90.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

34.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAReported
1187Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Coding6 benchmarks
Kimi Code Bench v2Provider exact
62.0%Display only
Source: MoonshotAI: Kimi K2.7 Code model cardProvenance: MoonshotAI reports Kimi Code Bench v2 at 62.0 for Kimi K2.7 Code. BenchLM treats this provider-run internal benchmark as display-only launch evidence.
ProgramBenchProvider exact

ProgramBench: Can Language Models Rebuild Programs From Scratch?

53.6%Display only
Source: MoonshotAI: Kimi K2.7 Code model cardProvenance: MoonshotAI reports Program Bench at 53.6 for Kimi K2.7 Code. BenchLM stores this provider-reported exact value separately from weighted coding benchmarks.
MLS-Bench LiteProvider exact
35.1%Display only
Source: MoonshotAI: Kimi K2.7 Code model cardProvenance: MoonshotAI reports MLS Bench Lite at 35.1 for Kimi K2.7 Code. BenchLM treats this sparse-coverage benchmark variant as display-only launch evidence.
cursorBench32Benchmark exact
49.7%Display only
Source: Cursor evals: CursorBench 3.2Provenance: Cursor reports Kimi K2.7 Code at this exact CursorBench 3.2 score on its public evals page. BenchLM stores it on the Kimi K2.7 Code row as a display-only coding-agent benchmark.
AA Coding IndexReported

Artificial Analysis Coding Index

60.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

47.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

66.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

10.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge6 benchmarks
Artificial Analysis Intelligence IndexReported
42.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

89.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

32.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-10.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

38.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

80.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Multimodal1 benchmark
Design Arena WebsiteReported

Design Arena Website Elo

1302Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

63.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

Kimi K2.7 Code Family

Code

Related Earlier Model

Kimi K2.6

Frequently Asked Questions

How does Kimi K2.7 Code perform overall in AI benchmarks?

Kimi K2.7 Code has 23 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is Kimi K2.7 Code good for knowledge and understanding?

Kimi K2.7 Code has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Kimi K2.7 Code good for coding and programming?

Kimi K2.7 Code ranks #38 out of 122 models in coding and programming benchmarks with an average score of 54.2. There are stronger options in this category.

Is Kimi K2.7 Code good for reasoning and logic?

Kimi K2.7 Code has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Kimi K2.7 Code good for agentic tool use and computer tasks?

Kimi K2.7 Code ranks #99 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 38. There are stronger options in this category.

Is Kimi K2.7 Code good for multimodal and grounded tasks?

Kimi K2.7 Code has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is Kimi K2.7 Code good for instruction following?

Kimi K2.7 Code has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Is Kimi K2.7 Code open source?

Yes, Kimi K2.7 Code is an open weight model created by Moonshot AI, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Does Kimi K2.7 Code have full benchmark coverage on BenchLM?

Not yet. Kimi K2.7 Code currently has 23 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Kimi K2.7 Code?

Kimi K2.7 Code has a published context window of 256K, which determines how much text it can process in a single interaction.

Last updated: July 23, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.