VQV Signal
According to a post on X by @ScaleAILabs, Scale AI Labs congratulated Thinking Machines on Inkling 2 Small and said the model ranks second on SWE Atlas QnA 1.1. The post also says Inkling 2 Small performs on par with Kimi-K3 on the full SWE-Bench Pro V2 set and with GPT-5.6 Terra on the hard subset. A follow-up points to labs.scale.com/leaderboard for more results. The available text is cut off before the full details.
According to a post on X by @ScaleAILabs, Scale AI Labs congratulated Thinking Machines on Inkling 2 Small and said the model ranks second on SWE Atlas QnA 1.1. The post also says Inkling 2 Small performs on par with Kimi-K3 on the full SWE-Bench Pro V2 set and with GPT-5.6 Terra on the hard subset. A follow-up points to labs.scale.com/leaderboard for more results. The available text is cut off before the full details.
AI-assisted summary based on the listed source.
Scale AI Labs congratulates Thinking Machines on Inkling 2 Small and says the model ranks second on SWE Atlas QnA 1.1 and performs on par with Kimi-K3 on the full SWE-Bench Pro V2 set and with GPT-5.6 Terra on the hard subset. A follow-up points to labs.scale.com/leaderboard for more results. Why it matters:...
The claims concern agentic coding, where models are tested on multi-step software tasks that developers care about when choosing tools. The results come from a social post, and VQV has not checked them against the full leaderboard data. Readers evaluating coding models should look at the leaderboard directly for the complete rankings.
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
VQV surfaced this signal because it is recent, relevant to AI Coding Tools, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.
