Stealth benchmarks · for providers

Run our benchmarks privately.

Daily runs and on-demand reruns. Results stay off the public leaderboard.

Get stealth benchmarks →See pricing

Our benchmark schedule:

Next benchmark run

public

AI Gateway — Kimi public release

Fri, Oct 30 · 9:45 AM

Benchmark Feed

Today · Oct 30, 2026
Oct 23, 2026

Sandbox Burst TTI

Composite score · Higher is better

Sandboxes

  1. 1Miosa99.4
  2. 2Isorun99.2
  3. 3PromigencePre-release99.0
  4. 4GravixlayerPre-release98.9
  5. 5Archil97.8
  6. 6Arker96.8
  7. 7Blaxel95.4
  8. 8Superserve95.2
  9. 9CreateOS94.9
  10. 10sfcompute94.2
  11. 11Beam92.8
  12. 12Cloudflare92.0
  13. 13Tenki91.4
  14. 14Buddy91.3
  15. 15Vercel90.2
  16. 16Declaw89.0
  17. 17Modal88.7
  18. 18Mosaic87.9
  19. 19Daytona87.4
  20. 20E2B84.6
  21. 21Tensorlake76.6
  22. 22Upstash75.7
  23. 23Novita74.5
  24. 24Microsandbox73.9
  25. 25Sail70.7
  26. 26Sandbox067.2
  27. 27Cloud Run63.4
  28. 28Freestyle61.7
  29. 29CodeSandbox0.0
  30. 30Run Cloud0.0
Oct 20, 2026
Oct 16, 2026
Oct 9, 2026

On these leaderboards?

Public benchmarks run on Fridays. Stealth benchmarks run your category's benchmarks daily and privately, with reruns and stealth-only benchmarks.

Get stealth benchmarks →

What ComputeSDK does

Benchmarks

ComputeSDK measures sandbox, storage, browser, and AI gateway providers against the same workloads and publishes the rankings free every week. Every workload and raw result is in the open methodology.

Built for agents

Create sandboxes, run commands, and read benchmark results over the REST API (OpenAPI) or the MCP server — llms.txt lists every machine-readable surface.

For providers

Stealth benchmarks run the public suite daily and privately for your provider, and the Market sells your idle capacity at your own price.