Inkling 2 Small is a sparse mixture-of-experts transformer announced by Thinking Machines on 5 November 2026. It carries 594 billion total parameters with 17 billion active, paired with a 292 million parameter vision encoder based on Perception Encoder. Context runs to one million tokens with compaction for long agent trajectories. It accepts text and image input and returns text; audio is not supported. Reasoning effort is variable.
On the scores the lab published: 86.3 percent on SWE-Bench Pro v2 Hard, 72.1 percent on DeepSWE v1.1, and 31 on the Artificial Analysis Intelligence Index. The lab also reports an internal misbehaviour rate of 14.9 against 66.8 for the first Inkling, where lower is better. That last figure cannot be reproduced outside the lab, but it indicates what the training was optimising for.
Training used NVFP4 pretraining on NVIDIA GB300 NVL72 racks and a nine-day reinforcement learning run across 2,048 GPUs.
Availability is API-only through Tinker, with weights closed at launch under the Tinker terms of use. Thinking Machines says it intends to release full weights under Apache 2.0 the following week, once external safety testing and red-teaming finish. No exact date has been confirmed and no pricing has been published.