The use case: how Artificial Analysis deploys E2B
Artificial Analysis runs every agentic benchmark task, for both its public leaderboards and its Optima custom-benchmark product, in its own isolated E2B sandbox. Each sandbox gives the agent a shell, file system, code execution and web access, and a single eval can fan out to many additional sandboxes for supporting services.
More reported results
Figures published in E2B’s case study. They are not independently measured by usedby.
Task durations from seconds to more than nine hours, on the same infrastructure.
In the customer’s words
Being able to hand off compute sandboxes to E2B has been fantastic as we've scaled from going from tens of sandboxes and benchmarks a day to hundreds of benchmarks and many thousands of sandboxes.Other AI tools used by Artificial Analysis
Other public relationships recorded on usedby.
Explore Artificial Analysis’s AI stack
Other companies using E2B
Customers across industries, with public evidence.
Arena (LMArena)Confirmed
ClickUpConfirmed
Effective AIConfirmed
GensparkConfirmed
GroqConfirmed
GumloopConfirmedGo straight to the source
Based on E2B’s published case study. We check the public evidence; the results are reported by the vendor.
e2b.dev- Source published
- Nov 10, 2026
- Last checked
- Nov 11, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: Hundreds of benchmarksChecked
Printed word for word on the page, near the name of Artificial Analysis.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Artificial Analysis.
- The publication dateChecked
Read from the page’s own metadata, never guessed.
- Artificial Analysis uses E2BChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Every benchmark task starts in its own E2B sandbox. That sandbox runs the agent loop and gives the model a full machine: a shell, a file system, code execution, and the web.