# Sandbox Arena

A benchmark that races two cloud code sandboxes on the same task.

Card 19 of 26 in Kevin Liu's collection. 2026. Infra and Data.

- Live: https://sandboxarena.vercel.app
- Source: https://github.com/Kevin-Liu-01/Sandbox-Arena
- Inks: 1
- Health 281, attack 103, defence 105, speed 105

## The numbers

- **24 commits**. Receipt: `git rev-list --count 0dae422af`
- **1 GitHub star**. Receipt: `gh api repos/Kevin-Liu-01/Sandbox-Arena --jq .stargazers_count (2026-11-01)`
- **3 check files**. Receipt: `gh api repos/Kevin-Liu-01/Sandbox-Arena/git/trees/0dae422af4e9189d982e981746d2379f73a28d2e?recursive=1 --jq ".tree[].path" | grep -cE <glob> (tree not truncated, 220 entries)`
- **4 commits per active day**. Receipt: `24 commits over 6 distinct commit dates, 2026-06-14 to 2026-07-27`

## Trait

**Fresh Sandbox**. Each run gets a fresh sandbox, deleted after, so its conditions clear every turn. Receipt: `Sandbox-Arena@0dae422af:lib/arena/orchestrator.ts:37-38, 49-51, 78-80; components/arena/TrialStudio.tsx:266`

## Moves

- Side By Side hits for 40 twice, 95% of the time. Two sandboxes start the same task at once and stream their logs side by side, so you watch the race live. Receipt: `Sandbox-Arena@0dae422af:lib/arena/orchestrator.ts:91-93, 121-128; README.md:7-10`
- Verified Finish hits for 80 and finishes a target under 35% health. Every task ends by checking its output against a known answer, so a fast but broken run scores zero. Receipt: `Sandbox-Arena@0dae422af:lib/arena/scoring.ts:100-101, 117-121; lib/arena/workloads.ts:30, 57, 99, 137, 169, 206, 247, 272, 306 (verifies); app/methodology/page.tsx:88-89`
- Slowest Runs hits for 95, 90% of the time. Rankings can sort providers by the time that 1 run in 20 exceeds, because averages hide rare long stalls. Receipt: `Sandbox-Arena@0dae422af:components/benchmarks/BenchmarkExplorer.tsx:13, 40-44, 93-94; app/benchmarks/page.tsx:45-47; README.md:26-28`
- Session Keys raises a 40% barrier. Your own account keys run one real trial, are read once, expire in ten minutes and never reach logs or the sandbox. Receipt: `Sandbox-Arena@0dae422af:lib/arena/credentials.ts:5-6, 63-70; lib/arena/security.ts:113-120; README.md:36-38`

Facts pinned at commit 0dae422af on 2026-07-27.

Back to every card: https://www.kevinliu.studio/