Thinking Machines' 26B looped-MoE Inklings 2 Mini beats GLM-5.2 and Opus 4.5 on benchmarks
ziqiao_ma · x · 2026-11-21
Thinking Machines Lab released Inklings 2 Mini: a looped-MoE model with 26.4B total params, only 4B active per token, running in 20 GB — yet it beats GLM-5.2 Full (753B, 40B active, 28x larger) and Claude Opus 4.5 on many benchmarks: Vibe Code Bench 77.9 vs 64.0, MCP Atlas 82.7, BrowseComp 79.0, DeepSWE 74.9, SWE-bench Verified 79.2 (GPT-5.2 Thinking: 80.9). The looped MoE approach (reusing a small active set across iterations) shows remarkable efficiency, though it still trails GPT-5.2 on ARC-AGI v2 and Automation Bench.
More from Models
- 'Time to Announce Math 3': AI Community Memes After Math Proof Breakthroughs — burny_tech · 2026-11-21
- Agent Arena Index debuts: Gemini 4 Neon lands #2 with 1336 points — arena · 2026-11-21
- Waddle-1 robot-use agent scores 81 on unseen bimanual tasks, beating GPT-6.2 Astra at 66 — ycombinator · 2026-11-21
- AI Posts Math Results on Navier–Stokes and Riemann Hypothesis — While We Still Call LLMs Parrots — haider1 · 2026-11-21
- alphaXiv Launches OpenResearch Intelligence Index, First Open Benchmark for Autoresearch — togethercompute · 2026-11-21
- 26.4B Inkling 2 Mini matches 975B model in 128 days, ~17x compute efficiency gain — teortaxesTex · 2026-11-21