Amazon Nova 2 Lite

Composite indexes

• Artificial Analysis Intelligence Index#82 of 142
  13independentIntelligence Index v4.3; high reasoning; estimatedArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 2.x#86 of 103
  16.1%independentTerminal-Bench 2.1; high reasoningArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: Claude Fable 5.1 at 91.4%

• LiveCodeBench#23 of 56
  71.1%independenthigh reasoningArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: Fugu at 92.9%

Agents and tool use

• τ²-Bench#36 of 88
  72.8%independenttelecom; high reasoningArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#83 of 103
  354independenthigh reasoningArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• GPQA Diamond#70 of 142
  81.1%independenthigh reasoningArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#91 of 147
  11.6%independentno tools; high reasoningArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#82 of 139
  0.3%independenthigh reasoningArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#85 of 139
  60.3%independenthigh reasoningArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#54 of 72
  63.8%independenthigh reasoningArtificial Analysis: Nova 2.0 Lite (high) ↗

  Leader: Claude Opus 5.5 at 87.7%

Other published results