KramaBench C
AI benchmark · Data
- Publisher
- Kramabench Official
- Tier
- C why
- Snapshot
What is KramaBench?
Evaluates data science agents on 104 manually curated tasks across archaeology, astronomy, biomedical research, environmental science, legal discovery, and wildfire prevention. Each task asks a system to discover, clean, combine, and analyze raw files to produce an answer. Reference pipelines and 633 subtasks support separate evaluations of end-to-end results, pipeline design, and individual data-task implementation. The primary score is the mean end-to-end task score, expressed as a percentage; partial credit depends on the answer type.
Tier C
Niche: a handful of models scored, or built by an RL vendor.
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.
- 5 models scored
- in curated RL directories (1 pt)
How we got to tier C
- Adoption: 5 models scored. Tier C.
- Not yet read on X.
- In curated RL directories: 1 point, a floor of none.
- Not yet confirmed by a line from its own site or paper.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Not on the map yet: no line from its own site or paper places it in a domain.
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.