data-agent-mnist
data-agent-mnist is The benchmark is an open harness you can run against your own data warehouse. It is ranked #1239 on the Dev Radar, in Databases, first seen 18 days ago and shared in 1 post (3.4k views).
What data-agent-mnist says about itself
Contribute to ClickHouse/data-agent-mnist development by creating an account on GitHub.
What people said about data-agent-mnist on X
We benchmarked 28 LLMs on agentic analytics: 201 real questions from our internal analytics agent, replayed against a full synthetic reconstruction of our data warehouse. @claudeai Fable 5.1 holds the top spot at 76.6% correctness. Thanks to @AnthropicAI for letting us benchmark the model ahead of the public release.…
— @ClickHouseDB, 18 days ago · 37 likes · see the post
Alternatives to data-agent-mnist
- Databricks — Genie One turned the trace data into a ranked list of what to fix, and a coding agent helped close the loop in an hour.
- radish.dhr.wtf — A Redis-compatible key-value store that runs inside a Cloudflare Durable Object. SQLite as the store, R2 as the cold…
- Build Your Own Convex — Grab a cup of tea and build a database piece by piece. An interactive guide to how Convex works, by Michael Cann.
- turbopuffer x Pragmatic Engineer — finally we can wrangle vectors for you if you'd like
- DuckDB — This post by @carlo_piovesan and @GeertjanW shows you how
- Redis — Two systems, one job: continuous compute and instant serving. @Databricks Real-Time Mode computes state as events…
data-agent-mnist in numbers
- Rank on the Dev Radar: #1239 of 1355
- Shared in 1 post by 1 account: @ClickHouseDB
- 3.4k views on those posts
- First seen 18 days ago, last shared 18 days ago
- Pricing seen by Jev: open source
- Market: Databases
FAQ
What is data-agent-mnist?
The benchmark is an open harness you can run against your own data warehouse It was first shared on X 18 days ago and is ranked #1239 on the Dev Radar.
Is data-agent-mnist free?
It is open source.
Who shared data-agent-mnist?
1 account on X, including @ClickHouseDB, in 1 post totalling 3.4k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.