Command A+

Composite indexes

• Artificial Analysis Intelligence Index#84 of 142
  13independentIntelligence Index v4.3; reasoningArtificial Analysis: Command A+ ↗

  Leader: Claude Opus 5.5 at 58

Coding

• SciCode#75 of 94
  38.5%independentreasoningArtificial Analysis: Command A+ ↗

  Leader: Claude Opus 5.5 at 66.9%

• Terminal-Bench 4.0#57 of 88
  0.5%independentreasoningArtificial Analysis: Command A+ ↗

  Leader: Claude Mythos 5.1 at 60.9%

• Terminal-Bench 2.x#81 of 103
  22.8%independentTerminal-Bench 2.1; reasoningArtificial Analysis: Command A+ ↗

  Leader: Claude Fable 5.1 at 91.4%

Agents and tool use

• τ²-Bench#31 of 88
  85%vendortelecomCohere blog: Introducing Command A+ ↗
  80.7%independenttelecom; reasoningArtificial Analysis: Command A+ ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#76 of 103
  500independentreasoningArtificial Analysis: Command A+ ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• GPQA Diamond#82 of 142
  76.1%independentreasoningArtificial Analysis: Command A+ ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#88 of 147
  12%independentno tools; reasoningArtificial Analysis: Command A+ ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#83 of 139
  0.3%independentreasoningArtificial Analysis: Command A+ ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#89 of 139
  52.7%independentreasoningArtificial Analysis: Command A+ ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#55 of 72
  63.2%independentreasoningArtificial Analysis: Command A+ ↗
  63%vendorCohere blog: Introducing Command A+ ↗

  Leader: Claude Opus 5.5 at 87.7%

• MMMU#1 of 1
  75.1%vendorCohere blog: Introducing Command A+ ↗

  Leader: Command A+ at 75.1%

Other published results