scBench B
AI benchmark · Science
- Built by
- Latch
- Domains
- Science
- On X
- @latchbio ↗
- Tier
- B why
- Snapshot
What is scBench?
scBench measures AI agents' ability to perform single-cell RNA-seq analysis tasks on real data snapshots, scored by deterministic graders.
Health and bio mostly
“scBench is a benchmark of 195 verifiable problems derived from practical single-cell RNA-seq workflows.”
github.com/latchbio/scbench ↗
Who built scBench
Led by LatchBio.
Tier B
Established: 15 or more models scored, or curated RL directories rate it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 17 models scored
- in curated RL directories (1 pt)
On X · unclear, low buzz, from 1 post about scBench in the last month
The only notable post refers to SlopCodeBench at scbench.ai, a different benchmark, so there is almost no discussion of the single-cell scBench.
How we got to tier B
- Adoption: 17 models scored. Tier B.
- On X: unclear, low buzz. “The only notable post refers to SlopCodeBench at scbench.ai, a different benchmark, so there is almost no discussion of the single-cell scBench.” No move.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where scBench sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-14 snapshot.