mirror of
https://github.com/hanzoai/site.git
synced 2026-11-21 01:07:08 +00:00
1 line
2.4 KiB
JSON
1 line
2.4 KiB
JSON
{"text":["Platform bench","Benchmarks","Agent platform","Cost and start-up","What an agent costs at rest, what a sandbox that runs a shell costs to start cold, and what one call costs at the margin, each beside the figure its alternative publishes. Every script re-runs to produce its row.","Latest","477 bytes","A dormant agent · Hanzo","as its alternative publishes ~1 MB · 2,198× · Unscored · September 2026 · Hanzo-measured","149.6 ms","A sandbox that runs a shell, cold · Hanzo","as its alternative publishes <200 ms · ~1 s · 1–3 s · pooled 35.8 ms · Unscored · September 2026 · Hanzo-measured","$0.00000063","One call, marginal cost · Hanzo","as its alternative publishes $0.05 credit · 79,614× · Unscored · September 2026 · Hanzo-measured","History","3 results across 3 metrics, newest first. Superseded runs stay, so a revision's progress can be read.","Measured","Subject","Metric","Value","Baseline","Result","Status","September 2026","Hanzo","A dormant agent","as its alternative publishes ~1 MB · 2,198×","Unscored","Frozen","Hanzo-measured","A sandbox that runs a shell, cold","as its alternative publishes <200 ms · ~1 s · 1–3 s · pooled 35.8 ms","One call, marginal cost","as its alternative publishes $0.05 credit · 79,614×","Conditions","A dormant agent: 1M agents: 455 MB on disk vs ~977 GB · $0.01/mo vs $22/mo at list · 310,270 agents/s written · 0.031 ms resume","A sandbox that runs a shell, cold: A JavaScript context alone is 0.16 ms against a published 2.79 ms (17×) — a different primitive, quoted beside, not instead","One call, marginal cost: ≈51 ms of compute per call · at a tenth of their price, 1B calls a month returns $3.7M after 25% to open source, three zones, a year of history and twice the infrastructure bill in people","the alternative figures are as their publishers state them, not re-run here","Hardware","M-series laptop, September 2026","Source","hanzoai/benchmarks · fleet, sandbox, pricing","Reproduce","node fleet/fleet.mjs /tmp/fleet && node sandbox/sandbox.mjs && node pricing/pricing.mjs","More Agent platform benchmarks","Fleet residency","Live agent footprint","Sandbox cold start","Every result for Platform bench on the shelf","How these are measured"],"links":["/benchmarks","/benchmarks?product=Agent%20platform#all","#history","https://github.com/hanzoai/benchmarks","/benchmarks/fleet","/benchmarks/goroutine","/benchmarks/sandbox","/benchmarks?q=Platform%20bench#all","/benchmarks#methods"]} |