Inkling 2 Small hits 81.7% on ARC-AGI-2, beating DeepSeek V4.1 Flash but trailing on ARC-AGI-3
teortaxesTex · x · 2026-11-17
ARC Prize published ThinkyMachines' Inkling 2 Small results on ARC-AGI (Verified): 96.5% on ARC-AGI-1 and 81.7% on ARC-AGI-2, beating DeepSeek V4.1 Flash 1017 (94.5% / 78.1%), but trailing on ARC-AGI-3 with 2.6% vs 5.8%. Total spend: $704 with the provider adapter, $858 standard.
teortaxesTex reads this as reassuring: Inkling 2 Small's scores likely come from "good data", while DeepSeek isn't even optimizing for ARC — a somewhat clear indication of DeepSeek's generic post-training quality and scale.
More from Models
- Google's Rumored 'Neon' Model Tied to Upsell Code, Likely a Pro-Tier Offering — testingcatalog · 2026-11-17
- User deliberately maxes out Anthropic quota to make it lose money this week — ryunuck · 2026-11-17
- Perturbing inputs improves LM pretraining distillation, new paper shows — DimitrisPapail · 2026-11-17
- Inkling-2-Small completes 911 enterprise tasks/hour on one B300 node, 43% cheaper than DeepSeek — ryanshrout · 2026-11-17
- Every used Claude Fable 5.2 to mine hundreds of meetings into a product philosophy doc — every · 2026-11-17
- Quantized Opus 5.5 says 'open' instead of 'run' — quantization quirks again — ryunuck · 2026-11-17