Database Paper Browser

Back to papers

ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines

Summary: ELT-Bench: end-to-end benchmark for AI agents to build ELT pipelines—integrating diverse sources, using data tools, writing code/SQL and orchestrating workflows (100 pipelines, 203 models). Eval of 4 agents with 6 LLMs: best agent succeeds on 11.3% of models (avg $1.41, 72.2 steps), exposing major automation gaps. (summarized by gpt-5-mini on Mar 13 2026)

Paper ID
14363
Venue
VLDB
Year
2026
Pagerank
4.1945683e-05
Overall Rank
10,320 | 28.21%
DOI
10.14778/3773749.3773750

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 9 of 9 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers