VerdictPal
Join

Models / Moonshot

Kimi K2.7 Code

Kimi · Released 2026-06-12

Moonshot's June 2026 coding-specialist Kimi release. Kimi's docs position `kimi-k2.7-code` as its most capable coding model, with a 256K context window, multimodal tool examples, mandatory thinking mode, and stronger long-horizon coding reliability than K2.6.

Budget coding agent model for repo-scale refactors, code review, MCP tool workflows, and long debugging loops where K2.6 was close but too token-hungry.

#47 of 168 on AA Index · current snapshot
43 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite55
Context262K
Input / 1M$0.95
Output / 1M$4.0
Knowledge cutoffopen
Output speed44 t/s
TTFT (default API)1.30s
Statussolid

Family profile

Best published score in each covered benchmark family.

70/100 avg
Reasoning
90
Coding
48
Agentic
67
Long context
75

4 tested benchmark families

Editor's note
K2.7 Code is not a general-chat replacement for K2.6; it is a coding-agent branch. The strongest launch claims are still first-party, so the tool stays solid rather than flagship until independent rows land in the ledger.
Benchmark placements

Where Kimi K2.7 Code places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
GPQA DiamondReasoning#48/ 18590Artificial Analysis2026-09-01
AA-LCRLong context#49/ 17975Artificial Analysis2026-09-01
Terminal-BenchAgentic#51/ 18467Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#53/ 18035Artificial Analysis2026-09-01
AA time to first tokenPerformance#54/ 186Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#57/ 18743Artificial Analysis2026-09-01
SciCodeCoding#59/ 18048Artificial Analysis2026-09-01
τ³-Bench BankingAgentic#59/ 10620Artificial Analysis2026-09-01
AA output speedPerformance#77/ 187Artificial Analysis2026-09-01
IFBenchReasoning#77/ 12763Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Kimi K2.7 Code shows up, it's highlighted.

ReasoningKimi K2.7 Code · 90
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingKimi K2.7 Code · 48
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticKimi K2.7 Code · 67
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextKimi K2.7 Code · 75
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for Kimi K2.7 Code in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context75%Artificial Analysis5
AA output speedPerformance44 t/sArtificial Analysis5
AA time to first tokenPerformance1.30sArtificial Analysis5
Artificial Analysis Intelligence IndexReasoning43%Artificial Analysis5
GPQA DiamondReasoning89.6%Artificial Analysis5
Humanity's Last ExamReasoning35%Artificial Analysis5
IFBenchReasoning63.13%Artificial Analysis5
SciCodeCoding47.5%Artificial Analysis5
τ³-Bench BankingAgentic20.21%Artificial Analysis5
Terminal-BenchAgentic67.42%Artificial Analysis5
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning90
Coding48
Agentic67
Long context75
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Kimi K2.7 Code. Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 37 catalog benchmarks have a sourced row for Kimi K2.7 Code.

Reasoning

Coding

Agentic

Long context

Performance

Changelog
  1. Released Kimi K2.7 Code with 256K context, mandatory thinking mode, multimodal tool examples, and reported 30% lower reasoning-token usage versus K2.6.
Sources