SID AI releases the SID-2 agent search model
Understand this story
SID AI released its second-generation agent search model SID-2 and a multi-agent version, SID-2 Swarm. According to MarkTechPost, the model decides on its own what to search next and returns ranked document IDs without needing to rebuild the index; the report says Swarm mode reaches 0.720 NDCG. SID-2 is available through SID's API and Baseten, priced at $0.25 per million input tokens and $1.00 per million output tokens; Swarm is $0.50 and $2.00; cached input is billed at 10% of the input price.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- MarkTechPostSID AI Releases SID-2 Agentic Search Model With 0.720 NDCG Swarm Mode
SID AI released SID-2, an agentic search model that searches data, reads results and returns ranked document IDs, along with SID-2 Swarm, in which multiple agents message each other and fork context to explore separate corpus slices. SID reports that a single agent matches Claude Opus 5.5 on retrieval quality and that the 12-agent Swarm scores 0.720 NDCG, above GPT-6 Astra at 0.704, on its self-built 506-question benchmark. SID-2 is available via SID's API, Baseten and a SageMaker path, priced from $0.25 per million input tokens, with model size and weights undisclosed.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 9Nov 18 19:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.