Inkling 2 Small posts top vision benchmark scores, endorsed by PyTorch creator
tessybarton · x · 2026-11-06
Soumith Chintala touts Inkling 2 Small's vision upgrades over Inkling 1. Its benchmark table leads open-weight rivals across DesignArena (1296–1428), ScreenSpot Pro (83.8/91.5), PerceptionBench (64.7%), GDP.pdf (25.2%) and MMMU Pro (81.6%), beating GLM 5.3 and Kimi K3 and nearing GPT-6.1.
More from Models
- Autonomous AI R&D Runs 'Extremely Dumb Experiments', Researcher Reports — panickssery · 2026-11-06
- Thinky Machines ships Inkling 2 Small, scoring 31 on AA Intelligence Index — SonglinYang4 · 2026-11-06
- Claude Opus 5 pulls off multi-level roleplay: staying in character while knowing it's acting — repligate · 2026-11-06
- Inkling 2 Small hits 46.8% Pass@1 on APEX-Agents, up 13 points over predecessor — ziqiao_ma · 2026-11-06
- Inkling 2 Small matches models 8-13x pricier at just $0.34 per task — echen · 2026-11-06
- Dev complains Anthropic free credits can't be used for Code or terminal — RileyRalmuto · 2026-11-06