Kimi K2.6

Composite indexes

• Artificial Analysis Intelligence Index#54 of 151
  27independentv4.3.2, reasoningArtificial Analysis: Kimi K2.6 ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#60 of 96
  0.5%independentreasoning, AA-runArtificial Analysis: Kimi K2.6 ↗

  Leader: Claude Sonnet 5.5 at 70.6%

• Terminal-Bench 2.x#41 of 105
  65.9%independentTerminal-Bench 2.1, reasoning, AA-runArtificial Analysis: Kimi K2.6 ↗

  Leader: Claude Fable 5.1 at 91.4%

• SciCode#38 of 100
  51.5%independentreasoning, AA-runArtificial Analysis: Kimi K2.6 ↗

  Leader: Claude Opus 5.5 at 66.9%

Agents and tool use

• τ²-Bench#6 of 89
  95.9%independenttelecom, reasoning, AA-runArtificial Analysis: Kimi K2.6 ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#56 of 109
  1026independentGDPval-AA v2.1, reasoningArtificial Analysis: Kimi K2.6 ↗

  Leader: Muse Wonder Full at 1857

Reasoning and knowledge

• GPQA Diamond#33 of 144
  91.1%independentreasoning, AA-runArtificial Analysis: Kimi K2.6 ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#46 of 153
  37.5%independentreasoning, no tools, AA-runArtificial Analysis: Kimi K2.6 ↗

  Leader: Claude Sonnet 5.5 at 64.5%

• CritPt#52 of 144
  8%independentreasoning, AA-runArtificial Analysis: Kimi K2.6 ↗

  Leader: Muse Wonder Full at 33%

Vision and long context

• AA Long Context Reasoning#26 of 144
  81%independentreasoning, AA-LCRArtificial Analysis: Kimi K2.6 ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#19 of 72
  79.4%independentreasoning, AA-runArtificial Analysis: Kimi K2.6 ↗

  Leader: Claude Opus 5.5 at 87.7%

Human preference

• LMArena Text#28 of 57
  1460independentarena entry "kimi-k2.6", 37,502 votes, checked 2026-09-25Arena (LMArena) text leaderboard ↗

  Leader: Gemini 4 Argon at 1525

• LMArena WebDev#40 of 58
  1509independentarena entry "kimi-k2.6", 9,587 votes, checked 2026-09-25Arena (LMArena) WebDev/Code leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results