Back to leaderboard

Daytona

Same Sandboxes task · View

#1 in Sandboxes

86B

Agent performance

Eval score
81%
Task success
Passed
Cost per runLower is better
$0.1931
Tool callsLower is better
8
ErrorsLower is better
1
RuntimeLower is better
1m 15s
Tokens usedLower is better
148,546

Discoverability

Discovery score
100%
Context7
llms.txt
MCP Server
Typed SDK
OpenAPI
Agent Skills

Eval details

Integration task
# Task Using https://www.daytona.io/docs/en/python-sdk/, complete the following task: Using Daytona, build me a script that runs a multi-step computation inside a Daytona sandbox...
Generated files
1
Trace tool calls
8
Completed
9/23/2026
Stderr
None captured
Full eval