← Back to the wire

SID AI Releases SID-2 Agentic Search Model With 0.720 NDCG Swarm Mode

AnnouncementModelNov 18, 2026

SID AI released SID-2, an RL-trained agentic search model that returns ranked document IDs, along with SID-2 Swarm. On SID's self-reported 506-question benchmark, 12-agent SID-2 Swarm scored 0.720 NDCG, above GPT-6 Astra at 0.704, while SID-2 Medium matched Claude Opus 5.5 at 0.585 NDCG in 3.11 seconds. SID-2 is available via SID's API and Baseten at $0.25 per million input tokens. Model size and weights are undisclosed, and all results are self-reported.

Receipt № 29531 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01med
www.marktechpost.comBloghttps://www.marktechpost.com/2026/11/17/sid-ai-sid-2-agentic-search-swarm/This source details SID-2's architecture and training, including its adaptive search loop, swarm coordination, reasoning-effort levels, and two-stage reinforcement learning with a latency penalty.
PRIMARY
BasetenCompanyGPT-6 AstraModelClaude Opus 5.5ModelSID AICompanySID-2ModelSID-2 SwarmModelSID-2 LowModel
Canonical: https://www.marktechpost.com/2026/11/17/sid-ai-sid-2-agentic-search-swarm/