Thinking Machines' Inkling-2-small tops US open-weight models on weight-space coding
keirp1 · x · 2026-11-07
Alex Krentsel reports that on weight-space programming (one-shot), Thinking Machines' Inkling-2-small took 2nd place overall and ranked first among US open-weight models.
The attached chart of open-weight models writing a Breakout network from scratch (PPO network at 500M steps = 1×) shows Kimi K3.1 Pro leading at 0.82×, Inkling-2 Small at 0.44×, well above DeepSeek V4 Pro (0.22×) and Step 5 Preview (0.33×), while Mistral Large 3 and GLM 5 sit at just 0.02×.
More from Models
- 'o1 was AI's biggest moment' — Epoch chart shows post-o1 gains turned incremental — flowersslop · 2026-11-07
- User: X's @bot beats Codex and Claude at video and social content generation — paigeinsf · 2026-11-07
- Google AI Overview refuses to answer 'nina tucker fursuit' search, called a coward — eigenrobot · 2026-11-07
- Google resets everyone's Gemini and Argon quota on Antigravity ahead of the weekend — rseroter · 2026-11-07
- GPT-6.2 and Fable 5.5 tipped for next week after Google Docs screenshots surface — imjustnewatai · 2026-11-07
- GPT Image 2.6 sweeps image leaderboards: Flare ~2x faster, Sunburst takes #1 — ArtificialAnlys · 2026-11-07