Kimi K2 0711

moonshotai/kimi-k2

MoonshotAI Kimi K2 0711 is a text‑only model released on 2025‑07‑11 by MoonshotAI. It supports a context length of 131,072 tokens, tool usage, and open weights, though it does not support reasoning. Input tokens are priced at $0.57 per M tokens and output tokens at $2.30 per M tokens.

  • tool use
  • open-weight

At a glance

providermoonshotai
releasedJan 1, 2024
context131K
input / M$0.57

Specifications

What the API gives you

Context window
131K tokens
Max output
100K tokens
Input price
$0.57 / 1M tokens
Output price
$2.30 / 1M tokens
Cache read
Modalities
text → text
Knowledge cutoff
Dec 31, 2024
Released
Jan 1, 2024

Measured evidence

Public benchmark record

Aider Polyglot
59.1%2026-07-23
Aider Polyglot
59.1%2026-07-27
Aider Polyglot
59.1%2026-07-28
Aider Polyglot
59.1%2026-07-29
Aider Polyglot
59.1%2026-07-30
Aider Polyglot
59.1%2026-07-31
Aider Polyglot
59.1%2026-08-01
Aider Polyglot
59.1%2026-08-02
Aider Polyglot
59.1%2026-08-05
Aider Polyglot
59.1%2026-08-03
Aider Polyglot
59.1%2026-08-09
Aider Polyglot
59.1%2026-08-04
Aider Polyglot
59.1%2026-08-06
Aider Polyglot
59.1%2026-08-07
Aider Polyglot
59.1%2026-08-14
Aider Polyglot
59.1%2026-08-08
Aider Polyglot
59.1%2026-08-10
Aider Polyglot
59.1%2026-08-11
Aider Polyglot
59.1%2026-08-18
Aider Polyglot
59.1%2026-08-12
Aider Polyglot
59.1%2026-08-19
Aider Polyglot
59.1%2026-08-13
Aider Polyglot
59.1%2026-08-15
Aider Polyglot
59.1%2026-08-20
Aider Polyglot
59.1%2026-08-16
Aider Polyglot
59.1%2026-08-17
Aider Polyglot
59.1%2026-08-21
Aider Polyglot
59.1%2026-08-27
Aider Polyglot
59.1%2026-08-22
Aider Polyglot
59.1%2026-08-23
Aider Polyglot
59.1%2026-08-24
Aider Polyglot
59.1%2026-08-25
Aider Polyglot
59.1%2026-08-26
Aider Polyglot
59.1%2026-08-28
Aider Polyglot
59.1%2026-08-29
Aider Polyglot
59.1%2026-08-30
Aider Polyglot
59.1%2026-08-31
Aider Polyglot
59.1%2026-09-01
Aider Polyglot
59.1%2026-09-02
Aider Polyglot
59.1%2026-09-03
Aider Polyglot
59.1%2026-09-04
BFCL
59.1%2026-07-29
BFCL
59.1%2026-07-31
BFCL
59.1%2026-07-30
BFCL
59.1%2026-08-02
BFCL
59.1%2026-08-01
BFCL
59.1%2026-08-05
BFCL
59.1%2026-08-03
BFCL
59.1%2026-08-09
BFCL
59.1%2026-08-04
BFCL
59.1%2026-08-06
BFCL
59.1%2026-08-07
BFCL
59.1%2026-08-14
BFCL
59.1%2026-08-10
BFCL
59.1%2026-08-08
BFCL
59.1%2026-08-18
BFCL
59.1%2026-08-11
BFCL
59.1%2026-08-15
BFCL
59.1%2026-08-12
BFCL
59.1%2026-08-13
BFCL
59.1%2026-08-19
BFCL
59.1%2026-08-16
BFCL
59.1%2026-08-20
BFCL
59.1%2026-08-27
BFCL
59.1%2026-08-17
BFCL
59.1%2026-08-21
BFCL
59.1%2026-08-22
BFCL
59.1%2026-08-23
BFCL
59.1%2026-08-24
BFCL
59.1%2026-08-28
BFCL
59.1%2026-08-25
BFCL
59.1%2026-08-26
BFCL
59.1%2026-08-29
BFCL
59.1%2026-08-30
BFCL
59.1%2026-08-31
BFCL
59.1%2026-09-01
BFCL
59.1%2026-09-02
BFCL
59.1%2026-09-03
BFCL
59.1%2026-09-04
Design Arena Coding
1064 Elo2026-07-28
Design Arena Coding
1064 Elo2026-07-27
Design Arena Coding
1064 Elo2026-07-30
Design Arena Coding
1064 Elo2026-07-29
Design Arena Coding
1064 Elo2026-07-31
Design Arena Coding
1063 Elo2026-08-02
Design Arena Coding
1062 Elo2026-08-05
Design Arena Coding
1063 Elo2026-08-01
Design Arena Coding
1061 Elo2026-08-09
Design Arena Coding
1063 Elo2026-08-03
Design Arena Coding
1063 Elo2026-08-04
Design Arena Coding
1058 Elo2026-08-14
Design Arena Coding
1062 Elo2026-08-06
Design Arena Coding
1061 Elo2026-08-10
Design Arena Coding
1063 Elo2026-08-07
Design Arena Coding
1052 Elo2026-08-18
Design Arena Coding
1061 Elo2026-08-08
Design Arena Coding
1053 Elo2026-08-15
Design Arena Coding
1061 Elo2026-08-11
Design Arena Coding
1060 Elo2026-08-12
Design Arena Coding
1059 Elo2026-08-13
Design Arena Coding
1051 Elo2026-08-19
Design Arena Coding
1058 Elo2026-08-27
Design Arena Coding
1051 Elo2026-08-20
Design Arena Coding
1052 Elo2026-08-16
Design Arena Coding
1052 Elo2026-08-17
Design Arena Coding
1058 Elo2026-08-21
Design Arena Coding
1058 Elo2026-08-22
Design Arena Coding
1058 Elo2026-08-23
Design Arena Coding
1057 Elo2026-08-28
Design Arena Coding
1058 Elo2026-08-24
Design Arena Coding
1058 Elo2026-08-25
Design Arena Coding
1058 Elo2026-08-26
Design Arena Coding
1057 Elo2026-08-29
Design Arena Coding
1057 Elo2026-08-30
Design Arena Coding
1057 Elo2026-08-31
Design Arena Coding
1057 Elo2026-09-01
Design Arena Coding
1056 Elo2026-09-02
Design Arena Coding
1054 Elo2026-09-03
Design Arena Coding
1053 Elo2026-09-04
Design Arena UI
1067 Elo2026-07-28
Design Arena UI
1068 Elo2026-07-27
Design Arena UI
1067 Elo2026-07-30
Design Arena UI
1068 Elo2026-07-29
Design Arena UI
1067 Elo2026-07-31
Design Arena UI
1068 Elo2026-08-02
Design Arena UI
1067 Elo2026-08-01
Design Arena UI
1066 Elo2026-08-05
Design Arena UI
1067 Elo2026-08-03
Design Arena UI
1063 Elo2026-08-09
Design Arena UI
1067 Elo2026-08-04
Design Arena UI
1061 Elo2026-08-14
Design Arena UI
1066 Elo2026-08-06
Design Arena UI
1066 Elo2026-08-07
Design Arena UI
1064 Elo2026-08-10
Design Arena UI
1064 Elo2026-08-08
Design Arena UI
1058 Elo2026-08-18
Design Arena UI
1064 Elo2026-08-11
Design Arena UI
1059 Elo2026-08-15
Design Arena UI
1064 Elo2026-08-12
Design Arena UI
1064 Elo2026-08-13
Design Arena UI
1058 Elo2026-08-19
Design Arena UI
1059 Elo2026-08-16
Design Arena UI
1058 Elo2026-08-20
Design Arena UI
1056 Elo2026-08-27
Design Arena UI
1058 Elo2026-08-17
Design Arena UI
1057 Elo2026-08-21
Design Arena UI
1057 Elo2026-08-22
Design Arena UI
1057 Elo2026-08-23
Design Arena UI
1057 Elo2026-08-24
Design Arena UI
1056 Elo2026-08-28
Design Arena UI
1058 Elo2026-08-25
Design Arena UI
1058 Elo2026-08-26
Design Arena UI
1057 Elo2026-08-29
Design Arena UI
1057 Elo2026-08-30
Design Arena UI
1057 Elo2026-08-31
Design Arena UI
1056 Elo2026-09-01
Design Arena UI
1056 Elo2026-09-02
Design Arena UI
1054 Elo2026-09-03
Design Arena UI
1052 Elo2026-09-04
Design Arena Website
1075 Elo2026-07-28
Design Arena Website
1075 Elo2026-07-30
Design Arena Website
1075 Elo2026-07-27
Design Arena Website
1075 Elo2026-07-29
Design Arena Website
1075 Elo2026-07-31
Design Arena Website
1074 Elo2026-08-02
Design Arena Website
1074 Elo2026-08-01
Design Arena Website
1074 Elo2026-08-05
Design Arena Website
1074 Elo2026-08-03
Design Arena Website
1073 Elo2026-08-09
Design Arena Website
1074 Elo2026-08-04
Design Arena Website
1070 Elo2026-08-14
Design Arena Website
1074 Elo2026-08-06
Design Arena Website
1074 Elo2026-08-07
Design Arena Website
1073 Elo2026-08-10
Design Arena Website
1073 Elo2026-08-08
Design Arena Website
1061 Elo2026-08-18
Design Arena Website
1073 Elo2026-08-11
Design Arena Website
1061 Elo2026-08-15
Design Arena Website
1072 Elo2026-08-12
Design Arena Website
1070 Elo2026-08-13
Design Arena Website
1061 Elo2026-08-19
Design Arena Website
1061 Elo2026-08-16
Design Arena Website
1061 Elo2026-08-20
Design Arena Website
1070 Elo2026-08-27
Design Arena Website
1061 Elo2026-08-17
Design Arena Website
1070 Elo2026-08-21
Design Arena Website
1070 Elo2026-08-22
Design Arena Website
1070 Elo2026-08-23
Design Arena Website
1070 Elo2026-08-24
Design Arena Website
1070 Elo2026-08-28
Design Arena Website
1070 Elo2026-08-25
Design Arena Website
1071 Elo2026-08-26
Design Arena Website
1070 Elo2026-08-29
Design Arena Website
1069 Elo2026-08-30
Design Arena Website
1070 Elo2026-08-31
Design Arena Website
1070 Elo2026-09-01
Design Arena Website
1068 Elo2026-09-02
Design Arena Website
1067 Elo2026-09-03
Design Arena Website
1066 Elo2026-09-04
LMArena Creative Writing
1324 Elo2026-07-21
LMArena Creative Writing
1324 Elo2026-07-27
LMArena Creative Writing
1324 Elo2026-07-30
LMArena Creative Writing
1324 Elo2026-08-02
LMArena Creative Writing
1324 Elo2026-08-03
LMArena Creative Writing
1324 Elo2026-08-06
LMArena Creative Writing
1323 Elo2026-08-12
LMArena Creative Writing
1323 Elo2026-08-21
LMArena Creative Writing
1323 Elo2026-08-27
LMArena Creative Writing
1323 Elo2026-09-01
LMArena Long Query
1325 Elo2026-07-21
LMArena Long Query
1326 Elo2026-07-27
LMArena Long Query
1326 Elo2026-07-30
LMArena Long Query
1326 Elo2026-08-02
LMArena Long Query
1326 Elo2026-08-03
LMArena Long Query
1325 Elo2026-08-06
LMArena Long Query
1327 Elo2026-08-12
LMArena Long Query
1327 Elo2026-08-21
LMArena Long Query
1325 Elo2026-08-27
LMArena Long Query
1325 Elo2026-09-01
LMArena Math
1367 Elo2026-07-21
LMArena Math
1367 Elo2026-07-27
LMArena Math
1367 Elo2026-07-30
LMArena Math
1368 Elo2026-08-02
LMArena Math
1368 Elo2026-08-03
LMArena Math
1367 Elo2026-08-06
LMArena Math
1367 Elo2026-08-12
LMArena Math
1367 Elo2026-08-21
LMArena Math
1366 Elo2026-08-27
LMArena Math
1367 Elo2026-09-01
LMArena Text
1417 Elo2026-07-21
LMArena Text
1418 Elo2026-07-27
LMArena Text
1418 Elo2026-07-30
LMArena Text
1418 Elo2026-08-10
LMArena Text
1418 Elo2026-08-02
LMArena Text
1418 Elo2026-08-06
LMArena Text
1418 Elo2026-08-03
LMArena Text
1418 Elo2026-08-21
LMArena Text
1418 Elo2026-08-12
LMArena Text
1418 Elo2026-08-27
LMArena Text
1418 Elo2026-09-01
SWE-bench Verified
65.4%2025-07-16
SWE-rebench
34.6% ± 0.92025-09-01tools
SWE-rebench
47.8% ± 1.22026-03-01tools

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • 70% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Business WritingProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Search. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for WritingProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Frontend & UIProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for CodingProvisional evidence

    56% of intended weighted task evidence across 4 independent sources; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 8 of 8 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    56% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • 55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • 50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Competition MathProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best Value LLMProvisional evidence

    36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsProvisional evidence

    29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesProvisional evidence

    29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingProvisional evidence

    23% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.

  • 20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • 20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 4 of 4 configured evaluation feeds currently have results.

  • 18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.

  • 13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Reasoning or LMArena Vision. 3 of 4 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

  1. #1Best Local LLM for Coding

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.