Perplexity's open decider model tops new Decision Index v0.3 leaderboard
antoine_chaffin · x · 2026-10-07
Perplexity's decider model improved from 56.4 to 61.5 on Decision Index v0.2 with the same backbone — 3.5 points above then-No.1 Jev — and immediately topped the newly released v0.3 leaderboard.
Most gains came from sane decisions like lifting the causal mask and using more training data (via tasksource). Weights are open on Hugging Face (perplexity-ai/pplx-decider-v1.1-27b), with an API for cheaper, better performance. Upcoming work: reranking, PII detection, stronger multimodal capabilities.
Related event: Perplexity Open-Sources pplx-decider-v1.1-27b, Tops HF Decision Index(8 posts)→
More from Models
- Token-based pricing is strange: unpredictable, decoupled from value, misaligned incentives — amankhan · 2026-10-07
- JevBench splits leaderboard: open-weight models and API providers now ranked separately — airesearch12 · 2026-10-07
- Hot take: active params barely matter for cyber capability evals — RL env coverage is key — teortaxesTex · 2026-10-07
- Decagon launches Voice 3 with Chord voice model and duplex architecture for customer agents — Scobleizer · 2026-10-07
- JEV-9B, a Qwen3.5-based calibrated decision model, trends on Hugging Face — autotrust · 2026-10-07
- "Astra Pause Syndrome": steering may be making models go silent, OpenAI has a workaround — thursdai_pod · 2026-10-07