Inkling 2 Mini benchmarks: 26B looped transformer beats same-size rivals on SWE tasks
clarejtbirch · x · 2026-11-21
Thinky Machines' open-weight Inkling 2 Mini, a 26B-parameter looped transformer, scores 20.1 on AA Index and runs on a laptop. Benchmark charts show it hitting 49% on DeepSWE v1.1 and 78% on SWE-bench Pro v2 Hard (51 tasks) at 50-60 theoretical tokens/s, well above Qwen3.8-27B and Gemma 4 models of similar size. Commenters highlight that the open release lets everyone research the interaction between CoT monitoring and looped transformers.
More from coding & agent
- Thinky Machines ships 26B looped transformer Inkling 2 Mini that runs on a laptop — DavideCrapis · 2026-11-21
- Multi-turn agentic RL on one TPU lifts Gemma 4 E2B from 9.4% to 95% win rate — Saboo_Shubham_ · 2026-11-21
- StepFun unveils Step 5 Preview at SF event focused on agent reliability and cost — StepFun_ai · 2026-11-21
- AI-made "game in a week" hype draws fire: it's a rough demo, not a game — AIandDesign · 2026-11-21
- Swapping RAG ranking for Jev lifted recruiter match precision from 44% to 92% — Select_Condition2805 · 2026-11-21
- What a Per-Agent Audit Trail Needs to Capture—and Where It Goes Incomplete — BlitzBallBruiser · 2026-11-21