Inkling-Small

Composite indexes

• Artificial Analysis Intelligence Index#43 of 142
  28independentIntelligence Index v4.3; reasoning; estimatedArtificial Analysis: Inkling Small ↗

  Leader: Claude Opus 5.5 at 58

Coding

• SciCode#43 of 94
  49.7%independentreasoningArtificial Analysis: Inkling Small ↗
  48.7%vendorThinking Machines Lab: Introducing Inkling-Small ↗

  Leader: Claude Opus 5.5 at 66.9%

• Terminal-Bench 4.0#48 of 88
  1%independentreasoningArtificial Analysis: Inkling Small ↗

  Leader: Claude Mythos 5.1 at 60.9%

• Terminal-Bench 2.x#56 of 103
  64.7%vendorTerminal-Bench 2.1, best harnessThinking Machines Lab: Introducing Inkling-Small ↗
  55.1%independentTerminal-Bench 2.1; reasoningArtificial Analysis: Inkling Small ↗

  Leader: Claude Fable 5.1 at 91.4%

• SWE-bench Verified#3 of 16
  80.2%vendorbash-only harnessThinking Machines Lab: Introducing Inkling-Small ↗

  Leader: Claude Sonnet 5 at 85.2%

• SWE-bench Pro#19 of 31
  55.9%vendorpublic setThinking Machines Lab: Introducing Inkling-Small ↗

  Leader: Claude Opus 5.5 at 89.9%

Agents and tool use

• GDPval-AA#35 of 103
  1269vendorGDPval-AA v2Thinking Machines Lab: Introducing Inkling-Small ↗

  Leader: Claude Opus 5.5 at 1846

• MCP Atlas#2 of 9
  79.6%vendorpublic setThinking Machines Lab: Introducing Inkling-Small ↗

  Leader: Kimi K3 at 84.2%

• BrowseComp#7 of 14
  77.4%vendorwith context managementThinking Machines Lab: Introducing Inkling-Small ↗

  Leader: GPT-6 Astra at 91.5%

Reasoning and knowledge

• GPQA Diamond#45 of 142
  89.5%independentreasoningArtificial Analysis: Inkling Small ↗
  89.5%vendorThinking Machines Lab: Introducing Inkling-Small ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#53 of 147
  47.8%vendorwith toolsThinking Machines Lab: Introducing Inkling-Small ↗
  33.3%independentno tools; reasoningArtificial Analysis: Inkling Small ↗
  31.6%vendortext only, no toolsThinking Machines Lab: Introducing Inkling-Small ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#45 of 139
  8.3%independentreasoningArtificial Analysis: Inkling Small ↗
  8.3%vendorThinking Machines Lab: Introducing Inkling-Small ↗

  Leader: GPT-5.6 Sol at 32.3%

• AIME 2026#4 of 13
  95.5%vendorAIME 2026Thinking Machines Lab: Introducing Inkling-Small ↗

  Leader: ERNIE 5.1 at 99.6%

• HMMT February 2026#2 of 8
  90.2%vendorHMMT Feb 2026Thinking Machines Lab: Introducing Inkling-Small ↗

  Leader: GLM-5.2 at 92.5%

• ARC-AGI-2#18 of 25
  40.1%independentsemi-private; XHigh effort; ARC Prize verified; $0.23/taskARC Prize leaderboard (evaluations data) ↗

  Leader: GPT-6 Astra at 95%

Vision and long context

• AA Long Context Reasoning#58 of 139
  75.7%independentreasoningArtificial Analysis: Inkling Small ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#40 of 72
  74%independentreasoningArtificial Analysis: Inkling Small ↗
  74%vendorstandard 10 optionsThinking Machines Lab: Introducing Inkling-Small ↗

  Leader: Claude Opus 5.5 at 87.7%

Other published results