Kimi K2 0905

moonshotai/kimi-k2-0905

MoonshotAI's Kimi K2 0905 is a text-to-text model. It supports a context length of 262,144 tokens and integrates with external tools.

  • tool use
  • structured outputs
  • open-weight

At a glance

providermoonshotai
releasedSep 4, 2025
context262K
input / M$0.60

Specifications

What the API gives you

Context window
262K tokens
Max output
100K tokens
Input price
$0.60 / 1M tokens
Output price
$2.50 / 1M tokens
Cache read
Modalities
text → text
Knowledge cutoff
Dec 31, 2024
Released
Sep 4, 2025

Measured evidence

Public benchmark record

Design Arena Coding
1128 Elo2026-07-28
Design Arena Coding
1128 Elo2026-07-27
Design Arena Coding
1128 Elo2026-07-30
Design Arena Coding
1128 Elo2026-07-29
Design Arena Coding
1128 Elo2026-07-31
Design Arena Coding
1127 Elo2026-08-02
Design Arena Coding
1127 Elo2026-08-05
Design Arena Coding
1127 Elo2026-08-01
Design Arena Coding
1126 Elo2026-08-09
Design Arena Coding
1127 Elo2026-08-03
Design Arena Coding
1127 Elo2026-08-04
Design Arena Coding
1123 Elo2026-08-14
Design Arena Coding
1127 Elo2026-08-06
Design Arena Coding
1126 Elo2026-08-10
Design Arena Coding
1127 Elo2026-08-07
Design Arena Coding
1117 Elo2026-08-18
Design Arena Coding
1126 Elo2026-08-08
Design Arena Coding
1117 Elo2026-08-15
Design Arena Coding
1126 Elo2026-08-11
Design Arena Coding
1125 Elo2026-08-12
Design Arena Coding
1123 Elo2026-08-13
Design Arena Coding
1116 Elo2026-08-19
Design Arena Coding
1122 Elo2026-08-27
Design Arena Coding
1116 Elo2026-08-20
Design Arena Coding
1117 Elo2026-08-16
Design Arena Coding
1117 Elo2026-08-17
Design Arena Coding
1122 Elo2026-08-21
Design Arena Coding
1123 Elo2026-08-22
Design Arena Coding
1123 Elo2026-08-23
Design Arena Coding
1122 Elo2026-08-28
Design Arena Coding
1123 Elo2026-08-24
Design Arena Coding
1123 Elo2026-08-25
Design Arena Coding
1123 Elo2026-08-26
Design Arena Coding
1122 Elo2026-08-29
Design Arena Coding
1122 Elo2026-08-30
Design Arena Coding
1122 Elo2026-08-31
Design Arena Coding
1122 Elo2026-09-01
Design Arena Coding
1120 Elo2026-09-02
Design Arena Coding
1118 Elo2026-09-03
Design Arena Coding
1117 Elo2026-09-04
Design Arena Website
1113 Elo2026-07-28
Design Arena Website
1113 Elo2026-07-30
Design Arena Website
1113 Elo2026-07-27
Design Arena Website
1114 Elo2026-07-29
Design Arena Website
1113 Elo2026-07-31
Design Arena Website
1112 Elo2026-08-02
Design Arena Website
1112 Elo2026-08-01
Design Arena Website
1112 Elo2026-08-05
Design Arena Website
1113 Elo2026-08-03
Design Arena Website
1111 Elo2026-08-09
Design Arena Website
1112 Elo2026-08-04
Design Arena Website
1108 Elo2026-08-14
Design Arena Website
1112 Elo2026-08-06
Design Arena Website
1112 Elo2026-08-07
Design Arena Website
1111 Elo2026-08-10
Design Arena Website
1111 Elo2026-08-08
Design Arena Website
1100 Elo2026-08-18
Design Arena Website
1111 Elo2026-08-11
Design Arena Website
1100 Elo2026-08-15
Design Arena Website
1111 Elo2026-08-12
Design Arena Website
1109 Elo2026-08-13
Design Arena Website
1100 Elo2026-08-19
Design Arena Website
1099 Elo2026-08-16
Design Arena Website
1100 Elo2026-08-20
Design Arena Website
1108 Elo2026-08-27
Design Arena Website
1100 Elo2026-08-17
Design Arena Website
1108 Elo2026-08-21
Design Arena Website
1109 Elo2026-08-22
Design Arena Website
1109 Elo2026-08-23
Design Arena Website
1109 Elo2026-08-24
Design Arena Website
1108 Elo2026-08-28
Design Arena Website
1109 Elo2026-08-25
Design Arena Website
1109 Elo2026-08-26
Design Arena Website
1108 Elo2026-08-29
Design Arena Website
1108 Elo2026-08-30
Design Arena Website
1108 Elo2026-08-31
Design Arena Website
1108 Elo2026-09-01
Design Arena Website
1107 Elo2026-09-02
Design Arena Website
1105 Elo2026-09-03
Design Arena Website
1104 Elo2026-09-04
LMArena Creative Writing
1350 Elo2026-07-21
LMArena Creative Writing
1350 Elo2026-07-27
LMArena Creative Writing
1350 Elo2026-07-30
LMArena Creative Writing
1350 Elo2026-08-02
LMArena Creative Writing
1350 Elo2026-08-03
LMArena Creative Writing
1349 Elo2026-08-06
LMArena Creative Writing
1348 Elo2026-08-12
LMArena Creative Writing
1348 Elo2026-08-21
LMArena Creative Writing
1347 Elo2026-08-27
LMArena Creative Writing
1347 Elo2026-09-01
LMArena Long Query
1351 Elo2026-07-21
LMArena Long Query
1351 Elo2026-07-27
LMArena Long Query
1351 Elo2026-07-30
LMArena Long Query
1351 Elo2026-08-02
LMArena Long Query
1351 Elo2026-08-06
LMArena Long Query
1351 Elo2026-08-03
LMArena Long Query
1352 Elo2026-08-12
LMArena Long Query
1352 Elo2026-08-21
LMArena Long Query
1351 Elo2026-08-27
LMArena Long Query
1351 Elo2026-09-01
LMArena Math
1397 Elo2026-07-21
LMArena Math
1398 Elo2026-07-27
LMArena Math
1398 Elo2026-07-30
LMArena Math
1398 Elo2026-08-02
LMArena Math
1398 Elo2026-08-03
LMArena Math
1398 Elo2026-08-06
LMArena Math
1398 Elo2026-08-12
LMArena Math
1398 Elo2026-08-21
LMArena Math
1396 Elo2026-08-27
LMArena Math
1396 Elo2026-09-01
LMArena Text
1418 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
71.2%2025-10-14
SWE-rebench
35.4% ± 0.72026-02-01tools

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.

  • 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.

  • 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.

  • 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 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 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 CodingProvisional evidence

    46% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 8 of 8 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 Frontend & UIProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena UI or LiveBench Coding. 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 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 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.

  • Best Local LLM for CodingProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 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.

  • Best LLM for OpenClawProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • 17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.

  • 17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 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 Code CompletionProvisional evidence

    13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 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 Berkeley Function Calling or LMArena Agent. 4 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 Berkeley Function Calling or LMArena Agent. 4 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

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

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