ClickHouse benchmarked analytical questions against 28 LLMs, including the latest Claude Fable 5.1, to evaluate agentic analytics.
Public source
Publisher name
Public post
For those work in data, our team benchmarked analytical questions against 28 LLMs, including the latest #Claude #Fable 5.1. The findings are really interesting even for…
Company
ClickHouse
The data platform powering the AI era. Speed, scale, and cost-efficiency - without compromise. clickhouse.com/cloud
- Industry
- Software Development
- Location
- Palo Alto, US
- Company size
- 501–1,000 employees
About ClickHouse
ClickHouse is a fast, open-source columnar database built for real-time data processing and analytics at scale. ClickHouse Cloud delivers the query speed and concurrency that applications demanding instant insight from large volumes of data require. As AI agents become more embedded in software, generating higher query volumes at tighter latency, ClickHouse provides a high-throughput, low-latency engine purpose-built for that workload.
See moreLatest activity
Latest activity from ClickHouse
28 signals
Presence & Recognition
ClickHouse is a proud sponsor of Rows & Columns Summit, happening September 22nd in San Francisco.
Research & Knowledge
ClickHouse streamed 113.2 billion stock-market quotes into ClickHouse Cloud, Snowflake, BigQuery, and Redshift Serverless while the same aggregate and drill-down queries ran throughout ingestion.
Presence & Recognition
ClickHouse hosted a webinar on Sept 17, 1PM Eastern, featuring 30 minutes on design decisions and 15 minutes of live Q&A with ClickHouse Engineering for quants, market data engineers, and platform architects.
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
LlamaIndex
LlamaIndex benchmarked over 92 tools on ParseBench.
Research & Knowledge
Onehouse
Onehouse conducted a comparison of five analytics engines including ClickHouse and StarRocks to evaluate their full SIMD support in C++ and in-memory MPP shuffle.
Research & Knowledge
Databricks
Databricks asked all 42 LLMs to process a 100 support tickets generated via a synthetic workload.
Research & Knowledge
Vals AI
Vals AI is releasing Tax Agent Bench, an agentic benchmark evaluating LLMs’ ability to do professional-level US corporate tax research consisting of 391 expert-written questions with each task evaluated with a rubric developed by tax practitioners.
Research & Knowledge
Endor Labs