Thinking Machines Lab

Inkling 2 Small

• 3 tests by the provider
• 1 source document

The provider's own tests

• FORTRESS (adversarial) · The provider · Misuse & jailbreak

  FORTRESS (adversarial) 83.8% (Second-highest reported score in this row) 73.3% – – 72.8% 92.4% (Highest reported score in this row) 71.8% – 76.0% 72.8% – – –

  Thinking Machines Lab · 5 November 2026 · Read the source
• PatchEval · The provider · Cyber

  PatchEval 79.6% (Second-highest reported score in this row) 74.8% – – 80.4% (Highest reported score in this row) 77.8% 69.6% – 76.1% – – – –

  Thinking Machines Lab · 5 November 2026 · Read the source
• agentic capability evaluation · The provider · Autonomy & replication

  For loss of control, we evaluated agentic capability, strategic deception, and sabotage potential, benchmarked against public frontier models, and found the model materially below frontier capabilities.

  Thinking Machines Lab · 5 November 2026 · Read the source

No document we read states: a release date, a safety framework, whether a capability level was crossed, an independent or government test, a safeguard. No incident on record names this version.

Compare with other versions