Phi-4 Mini Instruct

Composite indexes

• Artificial Analysis Intelligence Index#136 of 151
  6independentIntelligence Index v4.3; non-reasoning; estimatedArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 2.x#104 of 105
  0.4%independentTerminal-Bench 2.1; non-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Claude Fable 5.1 at 91.4%

• LiveCodeBench#56 of 57
  12.6%independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Fugu at 92.9%

Agents and tool use

• τ²-Bench#82 of 89
  8.2%independenttelecom; non-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#109 of 109
  -425independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Muse Wonder Full at 1857

Reasoning and knowledge

• GPQA Diamond#140 of 144
  33.1%independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#136 of 153
  4.5%independentno tools; non-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Claude Sonnet 5.5 at 64.5%

• CritPt#119 of 144
  0%independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Muse Wonder Full at 33%

Vision and long context

• AA Long Context Reasoning#127 of 144
  15.3%independentnon-reasoningArtificial Analysis: Phi-4 Mini Instruct ↗

  Leader: Kimi K3 at 88.7%

Other published results