Liquid AI launches d1-ultra decision model, tops Artificial Analysis Decision Index at 65.25
JosephJacks_ · x · 2026-10-16
Liquid AI has released d1-ultra, its most powerful decision model: it takes multimodal input (text + images) and returns probabilities for predefined answers, supporting yes/no questions, category selection, and scoring across 44 languages.
- Tops the Artificial Analysis Decision Index with a score of 65.25 and leads all eight categories of its 112-evaluation suite
- vs. Jev 1.14: average 76.7 vs 69.4, including Languages 80.2, Tools and Agents 82.8, Safety and Policy 85.8
- Available via Liquid AI's API at $0.042 per million input tokens; it generates no output tokens, with each question billed as a separate prompt
Related event: Liquid AI launches d1-ultra decision model, tops AA Decision Index(10 posts)→
More from Models
- Grok plans compared: is the $200 Ultra a better deal than $300 SuperGrok Heavy? — alexcovo_eth · 2026-10-16
- Early user: Opus 5.5 is far better than Astra at research ideation — menhguin · 2026-10-16
- Speculation: Meta's Spark 1.3 leap may come from OpenAI distillation, hence no open source — teortaxesTex · 2026-10-16
- Meta picks Apple's MLX as preferred local inference platform; Muse Spark Open runs on two M5 Ultra Mac Studios — awnihannun · 2026-10-16
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16