NEW: Inkling 2 Mini is the most efficient model we've tested: - #1...

- #1 on efficiency (cost vs. intelligence)
- #9 on intelligence (78.4) overall
- #1 on intelligence among open-weights models
- Lowest cost per correct answer ($25.80)
- Biggest accuracy gain from adding web search
It uses a looped transformer, which runs its middle layers three times for every token. That lets a 26B-parameter model reason more without generating more tokens, which keeps costs low. A model that size can't store as many facts, so it relies on search to fill the gaps, and that's where it gains the most.

Looping lets a model think more and write less. At this scale, its thought process remains monitorable; this may not stay the case. We’re also sharing a variable-loop research model to enable further study.
At 78.4 with Parallel Search, it passes Hy4 (75.4), the previous top open-weights model, at roughly one-fifth the cost per correct answer ($25.80 vs. $125 per 1K).



