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.

#87 of 131 on AA Index · current snapshot
33 AA Index · 13 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite63
ContextUnlisted
Input / 1M$0.60
Output / 1M$2.5
Knowledge cutoffunpublished
Output speed0 t/s
TTFT (default API)0.00s
Statussolid
KnowledgeReasoningMathCodingAgenticLong context
Knowledge
85
Reasoning
84
Math
95
Coding
85
Agentic
93
Long context
66

85average across 6 tested 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#7/ 3295Artificial Analysis2026-07-28
LiveCodeBenchCoding#9/ 2685Artificial Analysis2026-07-28
τ³-Bench BankingAgentic#16/ 14393Artificial Analysis2026-07-28
MMLU-ProKnowledge#20/ 3485Artificial Analysis2026-07-28
AA-LCRLong context#58/ 14366Artificial Analysis2026-07-28
IFBenchReasoning#59/ 12168Artificial Analysis2026-07-28
Humanity's Last ExamReasoning#84/ 14422Artificial Analysis2026-07-28
SciCodeCoding#84/ 14442Artificial Analysis2026-07-28
GPQA DiamondReasoning#89/ 14984Artificial Analysis2026-07-28
Artificial Analysis Intelligence IndexReasoning#103/ 14733Artificial Analysis2026-07-28
Terminal-BenchAgentic#123/ 14831Artificial Analysis2026-07-28
AA output speedPerformance#130/ 149Artificial Analysis2026-07-28
AA time to first tokenPerformance#130/ 149Artificial Analysis2026-07-28
Family context

The three highest-scoring carded models 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
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
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 · 93
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextKimi K2 Thinking · 66
  1. 1
    GPT-5 (high)
    76
  2. 2
    GPT-5.2 Codex (xhigh)
    76
  3. 3
    Kimi K3
    75
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.

13 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context66.33%Artificial Analysis6
AA output speedPerformance0 t/sArtificial Analysis6
AA time to first tokenPerformance0.00sArtificial Analysis6
AIMEMath94.67%Artificial Analysis6
Artificial Analysis Intelligence IndexReasoning32.7%Artificial Analysis6
GPQA DiamondReasoning83.8%Artificial Analysis6
Humanity's Last ExamReasoning22.3%Artificial Analysis6
IFBenchReasoning68.1%Artificial Analysis6
LiveCodeBenchCoding85.3%Artificial Analysis6
MMLU-ProKnowledge84.8%Artificial Analysis6
SciCodeCoding42.4%Artificial Analysis6
τ³-Bench BankingAgentic92.98%Artificial Analysis6
Terminal-BenchAgentic31.06%Artificial Analysis6
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
Agentic93
Long context66
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotxAIMiniMaxMetaZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

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

13 sourced rows

13 of 32 catalog benchmarks have a sourced row for Kimi K2 Thinking.

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Performance

Sources