KAT-Coder-Pro V2

Composite indexes

• Artificial Analysis Intelligence Index#63 of 142
  22independentv4.3.2 (AA estimate; independent evaluation forthcoming), non-reasoningArtificial Analysis: KAT Coder Pro V2 ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 2.x#35 of 103
  70%independentAA, Terminal-Bench 2.1, non-reasoningArtificial Analysis: KAT Coder Pro V2 ↗

  Leader: Claude Fable 5.1 at 91.4%

Agents and tool use

• τ²-Bench#21 of 88
  89.5%independentAA, telecom, non-reasoningArtificial Analysis: KAT Coder Pro V2 ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#68 of 103
  720independentGDPval-AA v2.1, non-reasoningArtificial Analysis: KAT Coder Pro V2 ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• Humanity’s Last Exam#78 of 147
  16.1%independentAA, no tools, non-reasoningArtificial Analysis: KAT Coder Pro V2 ↗

  Leader: Claude Opus 5.5 at 61.4%

• GPQA Diamond#57 of 142
  85.5%independentAA, non-reasoningArtificial Analysis: KAT Coder Pro V2 ↗

  Leader: GPT-6 Astra at 96.1%

• CritPt#102 of 139
  0%independentAA, non-reasoningArtificial Analysis: KAT Coder Pro V2 ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#67 of 139
  73%independentAA, non-reasoningArtificial Analysis: KAT Coder Pro V2 ↗

  Leader: Kimi K3 at 88.7%

Other published results