Amazon Nova 2 Pro (Preview)

Composite indexes

• Artificial Analysis Intelligence Index#80 of 142
  14independentIntelligence Index v4.3; medium reasoning; estimatedArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 2.x#76 of 103
  29.6%independentTerminal-Bench 2.1; medium reasoningArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: Claude Fable 5.1 at 91.4%

• LiveCodeBench#20 of 56
  73%independentmedium reasoningArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: Fugu at 92.9%

Agents and tool use

• τ²-Bench#16 of 88
  92.7%independenttelecom; medium reasoningArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#80 of 103
  456independentmedium reasoningArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• GPQA Diamond#74 of 142
  78.5%independentmedium reasoningArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#108 of 147
  9.4%independentno tools; medium reasoningArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#115 of 139
  0%independentmedium reasoningArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#81 of 139
  64%independentmedium reasoningArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#51 of 72
  64.5%independentmedium reasoningArtificial Analysis: Nova 2.0 Pro Preview (medium) ↗

  Leader: Claude Opus 5.5 at 87.7%

Other published results