VerdictPal
Join

Models / Moonshot

Kimi K2 Thinking

Kimi K2 · Released 2025-11-06

AA Intelligence Index 32.7. Listed on Artificial Analysis with API pricing $0.6/$2.5 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#114 of 184 on AA Index · current snapshot
22 AA Index · 11 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite61
ContextUnlisted
Input / 1M$0.60
Output / 1M$2.5
Knowledge cutoffunpublished
Statussolid

Family profile

Best published score in each covered benchmark family.

75/100 avg
Knowledge
85
Reasoning
84
Math
95
Coding
85
Agentic
31
Long context
72

6 tested benchmark families

Benchmark placements

Where Kimi K2 Thinking 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
AIMEMath#8/ 3795Artificial Analysis2026-09-10
LiveCodeBenchCoding#11/ 3185Artificial Analysis2026-09-10
MMLU-ProKnowledge#24/ 3985Artificial Analysis2026-09-10
IFBenchReasoning#59/ 12768Artificial Analysis2026-09-10
AA-LCRLong context#106/ 18272Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#110/ 18524Artificial Analysis2026-09-10
GPQA DiamondReasoning#117/ 19084Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#123/ 18822Artificial Analysis2026-09-10
Terminal-BenchAgentic#155/ 18931Artificial Analysis2026-09-10
AA output speedPerformance#159/ 190Artificial Analysis2026-09-10
AA time to first tokenPerformance#159/ 190Artificial Analysis2026-09-10
Family context

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

KnowledgeKimi K2 Thinking · 85
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningKimi K2 Thinking · 84
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
MathKimi K2 Thinking · 95
  1. 1
    OpenAI o3
    99
  2. 2
    GPT-5 (medium)
    99
  3. 3
    Grok 4
    99
CodingKimi K2 Thinking · 85
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticKimi K2 Thinking · 31
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextKimi K2 Thinking · 72
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

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

11 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context72%Artificial Analysis7
AA output speedPerformance0 t/sArtificial Analysis7
AA time to first tokenPerformance0.00sArtificial Analysis7
AIMEMath94.67%Artificial Analysis7
Artificial Analysis Intelligence IndexReasoning22%Artificial Analysis7
GPQA DiamondReasoning83.8%Artificial Analysis7
Humanity's Last ExamReasoning23.8%Artificial Analysis7
IFBenchReasoning68.1%Artificial Analysis7
LiveCodeBenchCoding85.3%Artificial Analysis7
MMLU-ProKnowledge84.8%Artificial Analysis7
Terminal-BenchAgentic31.06%Artificial Analysis7
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.

Knowledge85
Reasoning84
Math95
Coding85
Agentic31
Long context72
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

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

11 sourced rows

11 of 37 catalog benchmarks have a sourced row for Kimi K2 Thinking.

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Performance

Sources

Questions this model page answers

Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.

What is Kimi K2 Thinking?

Kimi K2 Thinking is a Moonshot model: AA Intelligence Index 32.7. Listed on Artificial Analysis with API pricing $0.6/$2.5 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

What is Kimi K2 Thinking for?

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

What does Kimi K2 Thinking cost?

Kimi K2 Thinking lists $0.60 input and $2.5 output per 1M tokens. Pricing last checked 2026-08-01.

How large is the Kimi K2 Thinking context window?

Kimi K2 Thinking publishes a Unlisted token context window.

What is the VerdictPal status of Kimi K2 Thinking?

Kimi K2 Thinking carries Solid status on the model atlas.

The Pack · Editorial newsletter

New tools in your inbox. Free.

One short email when a tool ships or changes status. No tracking, no third-party analytics. Unsubscribe in one click.