Thoughtful Lab: Inkling 2 Small scores 31.87 on PostTrainBench, level with GPT-5.6 (Sol) and Opus 4.8

Thoughtful Lab, which says it partnered with Thinking Machines to evaluate Inkling 2 Small, reports that the model scores 31.87 on PostTrainBench, a test of how well a model can improve other models on its own. It lists Kimi K3 at 31.48 and GLM 5.2 at 30.40, and puts GPT-5.6 (Sol) and Opus 4.8 at about 31. It notes the model has 17B active parameters.

These are the evaluator's own figures.