Archil vs Luxor

Sandbox Benchmark Comparison · Updated November 20, 2026

Archil was faster in 1 of 2 shared sandbox benchmarks, and 1 was roughly even.

Head to head

  • Time to interactive · lower is better
    Archil faster2.12x
    Archil
    691ms
    Luxor
    1.47s
  • Total workload time · lower is better
    Roughly even
    Archil
    54.44s
    Luxor
    56.95s

Burst TTI

November 20, 2026

Archil

100% success
Median
691ms
p95
740ms
p99
744ms

Luxor

100% success
Median
1.47s
p95
1.68s
p99
1.71s

Median time to interactive over time

15 runs · August 28, 2026 to November 20, 2026
ArchilLuxor

DAX

November 20, 2026

Archil

100% success
Median
54.44s

Luxor

100% success
Median
56.95s

Median total workload time over time

3 runs · November 6, 2026 to November 20, 2026
ArchilLuxor

Cost per DAX run

Archil

Per-sandbox wall clock
$0.0041per run
54.44s median at $0.2700/hr

$0.27/sandbox-hr — but Archil sandboxes are fixed at 2 vCPU / 4 GB, so the spec doesn't match 8/16 and the comparison isn't apples-to-apples.

Source pricing page

Luxor

Per-second wall clock
$0.010per run
56.95s median at $0.6624/hr

$0.000014/vCPU-s + $0.0000045/GiB-s; usage draws from monthly workspace credits first.

Source pricing page
Compare sandbox costs across all providers
Work at Archil or Luxor? See where you stand every day, with full run logs, not just on benchmark Friday.Get stealth benchmarks

Methodology

  • One workload, every provider. The same script, payload, and model hit every provider, addressed the way its own API expects. Nobody gets a tuned or special path.
  • Repeated on a schedule. Every suite runs many iterations per provider, automated on a recurring schedule, so results reflect steady state rather than one lucky request.
  • Raw results published. Every run is committed as JSON to the public benchmarks repo, next to the code that produced it. Nothing is cherry-picked or held back.
  • How this comparison is built. Each benchmark compares the two providers' medians; results within 5% count as roughly even. A comparison is published when both providers have at least one successful run in the same benchmark from the last 30 days. A benchmark only gets a verdict when both providers completed at least 50% of its runs. If a provider’s latest run of a benchmark failed, its most recent successful run from that window is used instead.
Read the full methodology

Frequently asked questions

Have another question? Email us.

Archil was faster in 1 of 2 shared sandbox benchmarks, and 1 was roughly even. In Burst TTI (November 20, 2026), Archil had a median time to interactive of 691ms versus 1.47s for Luxor, 2.12x faster. In DAX (November 20, 2026), Archil had a median total workload time of 54.44s and Luxor 56.95s, which counts as roughly even.

Both providers have results in 2 sandbox benchmarks: Burst TTI and DAX. All of them have a speed verdict.

Success rates in the latest runs: Burst TTI: Archil 100%, Luxor 100%; DAX: Archil 100%, Luxor 100%.

Burst TTI and DAX results are from November 20, 2026.