SubQ Snap 1.1 ties for first on Artificial Analysis Decision Index with 384K context
ArtificialAnlys · x · 2026-10-23
Subquadratic released SubQ Snap 1.1, a decision model that ties d1-ultra and Elephant 9B for first place (65) on the Artificial Analysis Decision Index v1.0, 8 points ahead of the next model, Jev 1.14 (57).
Key facts:
- Hallucination control: 86% non-hallucination rate on AA-Omniscience-Decision (share of wrong answers where the model said "I don't know"), second only to Elephant 9B (93%) and ahead of d1-ultra (85%); attempt rate is 32% vs 42% for d1-ultra and 18% for Elephant 9B.
- Context: 384K tokens, far beyond d1-ultra's 32K and Elephant 9B's 16K.
- Pricing: $0.04 per 1M input tokens; $30 per 1M tasks, in line with d1-ultra ($32) but 3.6x the cost of equally-scoring Elephant 9B ($8.4).
- Scores 18% on HLE-MultiChoice, level with Elephant 9B and above d1-ultra (15%).
Related event: SubQ Snap 1.1 Tops Decision Model Index with 384K Context(2 posts)→
More from Models
- OpenAI blocks manual reset with 13% usage left: 'no reset needed right now' — AccomplishedSugar490 · 2026-10-23
- Meta's 816B Muse Spark Open scores 39, losing to 180B Qwen3.8-Flash-Next at 40 — BTA_Labs · 2026-10-23
- Gemini refuses to generate image in Docs, blames document size limit — viksit · 2026-10-23
- Dev jokes his true calling is telling everyone to try the latest DeepSeek — intellectronica · 2026-10-23
- PolyAI unveils Dialog-RSN-1: audio-native voice model answering in under 300ms — matthen2 · 2026-10-23
- Konrad Kording: little evidence that chatting with AI personalizes it — KordingLab · 2026-10-23