The use case: how Martian deploys Daytona
Martian uses Daytona's sandbox infrastructure within its open-source ARES framework to run reinforcement learning for LLM coding agents. Daytona provisions many isolated, parallel sandboxes on demand so agents can work through coding tasks and benchmarks simultaneously and receive real-time evaluations.
More reported results
Figures published in Daytona’s case study. They are not independently measured by usedby.
20K+ sandboxes provisioned in one week with Daytona
3 months of engineering time saved
In the customer’s words
Daytona has hugely simplified and sped up our agentic training and evaluation stack with their sandbox infrastructure. It sits quietly in the background, ensuring every environment and every agent runs exactly as ARES requires.Other companies using Daytona
Customers across industries, with public evidence.
AfterQueryConfirmed
AsteroidConfirmed
BenchFlowConfirmed
CapyConfirmed
HandshakeConfirmed
Laude InstituteConfirmedGo straight to the source
Based on Daytona’s published case study. We check the public evidence; the results are reported by the vendor.
daytona.io- Last checked
- Oct 27, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 95%Checked
Printed word for word on the page, near the name of Martian.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Martian.
- Martian uses DaytonaChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
This isolated parallelization enables agents to complete demanding benchmarks like Terminal-Bench 2.0 in 20 minutes, compressing feedback loops and supporting faster, iterative research cycles.