ThinkyMachines launches Inkling 2 Small, topping visual benchmarks against GLM, DeepSeek and Kimi
yb2698 · x · 2026-11-06
ThinkyMachines released Inkling 2 Small, scoring 31 on the AA Intelligence Index — a big jump over its predecessor. The model is available for fine-tuning and inference on Tinker today, with a full open-weight release planned soon.
The published visual reasoning/creation benchmark table shows it leading most comparisons:
- GDP.pdf 25.2%, well above GLM-5.3-Flash (15.4%), DeepSeek-V4.1-Flash (17.2%), and Kimi K3 (22.0%)
- Best-in-class on MMMU Pro (81.6%), PerceptionBench (64.7%), and ScreenSpot Pro (83.8/91.5%)
- Clear lead on Chartography (36.7/80.4%); tops AA-3D with 1021
- Code Arena (WebDev) 1653, slightly behind DeepSeek's 1665 and Kimi K3's 1656
Hugo LaRochelle, a Hugging Face leadership member, reposted praising its significantly improved vision understanding and creation.
Related event: Thinking Machines Launches Inkling 2 Small(65 posts)→
More from Models
- OpenAI's AI finds 948 working Linux kernel privilege escalation bugs for $1.2M in API credits — Fcking_Chuck · 2026-11-06
- Custom GPTs die Dec 11: if you use someone else's GPT, you can't migrate it — Ok_Negotiation_2587 · 2026-11-06
- Thinking Machines Ships Inkling 2 Small: 68-Hour Pretrain, Top Non-China Open-Weights Model — Latent Space · 2026-11-06
- Kimi K3.1 and Tencent Hy4 accused of gutting cybersecurity skills from open-weight models — Fresh_Sun_1017 · 2026-11-06
- On the METR graph: insiders seeing AECI tasks is weak evidence, not zero evidence — gleech · 2026-11-06
- Daily AI brief: GPT-6.2 imminent, Claude Personal Finance beta, METR says Anthropic progress up 1.9x — testingcatalog · 2026-11-06