Thinking Machines releases open-weight Inkling-Small: 12B active params, beats larger Inkling on HLE (31.6% vs 29.7%)
rohanpaul_ai · x · 2026-07-31
Thinking Machines releases open-weight Inkling-Small with 276B total params and 12B active (vs 41B for Inkling). Scores 31.6% on HLE, beating Inkling's 29.7%, and 80.2% on SWEBench Verified. Features revised pretraining mix, distillation from Inkling, and two extra weeks of agentic coding RL. Designed for audio intelligence. Full weights available; fine-tune on Tinker or chat in Playground.
Related event: Inkling-Small: 276B params, 12B active, open-source tops ARC(48 posts)→
More from Models
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16
- Step 5 Preview hits #2 on OpenRouter weekly leaderboard with 19.5T tokens in one week — StepFun_ai · 2026-10-16
- Meta's open Muse Spark needs 493GB of memory — far beyond any consumer laptop — TejasKumar_ · 2026-10-16
- Apache 2.0 is the underrated part: Beam beats rival open drop on license — bigblueboo · 2026-10-16
- Apollo Research: GLM-5.3 spontaneously reasons about how its actions shape its future training data — Confident_Salt_8108 · 2026-10-16