Claude Opus 5.5

Composite indexes

• Artificial Analysis Intelligence Index#1 of 142
  58independentv4.3.2, max effortArtificial Analysis: Claude Opus 5.5 ↗
  51independentv4.3.2, medium effort (API default)Artificial Analysis: Claude Opus 5.5 (medium) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• SciCode#1 of 94
  66.9%independentAA run, max effortArtificial Analysis: Claude Opus 5.5 ↗

  Leader: Claude Opus 5.5 at 66.9%

• Terminal-Bench 4.0#2 of 88
  66.4%vendorxhigh effort, Claude Code harness, ±2.6 SEAnthropic: Introducing Claude Opus 5.5 ↗
  59.6%independentAA run (Terminal-Bench 4.0), max effortArtificial Analysis: Claude Opus 5.5 ↗

  Leader: Claude Mythos 5.1 at 60.9%

• SWE-bench Pro#1 of 31
  89.9%vendorAnthropic-run, max effort, avg of 5 trials (set not specified)Claude Opus 5.5 System Card, Table 8.1.A ↗

  Leader: Claude Opus 5.5 at 89.9%

Agents and tool use

• GDPval-AA#1 of 103
  1846independentGDPval-AA v2.1, max effortArtificial Analysis: Claude Opus 5.5 ↗

  Leader: Claude Opus 5.5 at 1846

• OSWorld-Verified#4 of 16
  81.8%vendorOSWorld 2.0 partial score (strict 48.7%), max effortClaude Opus 5.5 System Card, Table 8.1.A ↗

  Leader: Kimi K3 at 84.8%

Reasoning and knowledge

• Humanity’s Last Exam#1 of 147
  67.7%vendorwith tools, max effortAnthropic: Introducing Claude Opus 5.5 ↗
  64.4%vendorno tools, max effortClaude Opus 5.5 System Card, Table 8.1.A ↗
  61.4%independentAA run, no tools, max effortArtificial Analysis: Claude Opus 5.5 ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#3 of 139
  31.7%independentAA run, max effortArtificial Analysis: Claude Opus 5.5 ↗

  Leader: GPT-5.6 Sol at 32.3%

• ARC-AGI-2#2 of 25
  93.3%independenthigh effort; ARC Prize verified, cost $0.41/taskARC Prize leaderboard data (semi-private) ↗
  91.7%independentmax effort; ARC Prize verified, cost $1.85/taskARC Prize leaderboard data (semi-private) ↗

  Leader: GPT-6 Astra at 95%

Vision and long context

• AA Long Context Reasoning#5 of 139
  84.7%independentAA-LCR v1.1, max effortArtificial Analysis: Claude Opus 5.5 ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#1 of 72
  87.7%independentAA run, max effortArtificial Analysis: Claude Opus 5.5 ↗

  Leader: Claude Opus 5.5 at 87.7%

Human preference

• LMArena WebDev#1 of 54
  1818independentclaude-opus-5.5-max; 1,219 votes (preliminary)LMArena Code Arena | WebDev leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results