Phi-4 Mini Instruct

Composite indexes

• Artificial Analysis Intelligence Index#127 of 142
  6independentIntelligence Index v4.3; non-reasoning; estimatedArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 2.x#102 of 103
  0.4%independentTerminal-Bench 2.1; non-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Claude Fable 5.1 at 91.4%

• LiveCodeBench#55 of 56
  12.6%independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Fugu at 92.9%

Agents and tool use

• τ²-Bench#81 of 88
  8.2%independenttelecom; non-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#103 of 103
  -425independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• GPQA Diamond#138 of 142
  33.1%independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#130 of 147
  4.5%independentno tools; non-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#114 of 139
  0%independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#122 of 139
  15.3%independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Kimi K3 at 88.7%

Other published results