Inkling-Small | Terminal-Bench 2.1 — Thinking Machines internal coding harness

Thinking Machines Lab's Inkling-Small evaluation results on Terminal-Bench 2.1 — Thinking Machines internal coding harness

Score: 64.7%

Reasoning level: effort=0.99

Source

Inkling-Small (Registry No. 160002)

Thinking Machines Lab

Terminal-Bench 2.1 — Thinking Machines internal coding harness