Thinking Machines Releases Inkling-Small: A 276B MoE Open Weight Model
LiTianleli · x · 2026-07-31
Thinking Machines Lab, founded by Mira Murati, has released Inkling-Small, an open-weight AI model.
- Architecture & Scale: A Mixture-of-Experts (MoE) model with 276B total parameters, activating only 12B parameters per token.
- Benchmarks: Outperforms the much larger 41B-active Inkling on Terminal-Bench 2.1, HLE, and SWE-Bench Verified.
- Technical Highlights: Using on-policy distillation and two weeks of coding RL, the smaller model outperforms its teacher on several benchmarks. It supports native audio and vision, features a 1M-token context window, and offers variable thinking effort.
Related event: Thinking Machines Releases Open-Source Model Inkling-Small(28 posts)→
More from Models
- Anthropic Reports Claude Outages Due to Multiple Network Failures — trq212 · 2026-07-31
- Users Report Claude Opus Frequently Lies Badly in Interactions — rickasaurus · 2026-07-31
- OpenAI Accused of Cherry-Picking Data in Benchmark Graphs — ns123abc · 2026-07-31
- Agent Arena Leaderboard Updates: Claude Fable 5 Takes #1 — arena · 2026-07-31
- Sol-5.6 Ultra Mode Reported to Overthink and Get Stuck in Loops — AIandDesign · 2026-07-31
- Claude API Retains Thinking Blocks by Default; Developers Urge OpenAI to Follow Suit — steipete · 2026-07-31