Beam vs Luxor

Sandbox Benchmark Comparison · Updated November 20, 2026

Beam and Luxor were each faster in 1 of 2 shared sandbox benchmarks.

Head to head

  • Time to interactive · lower is better
    Beam faster2.26x
    Beam
    649ms
    Luxor
    1.47s
  • Total workload time · lower is better
    Luxor faster1.97x
    Beam
    112.09s
    Luxor
    56.95s

Burst TTI

November 20, 2026

Beam

100% success
Median
649ms
p95
867ms
p99
877ms

Luxor

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

Median time to interactive over time

16 runs · August 28, 2026 to November 20, 2026
BeamLuxor

DAX

November 20, 2026

Beam

100% success
Median
112.09s

Luxor

100% success
Median
56.95s

Median total workload time over time

11 runs · September 16, 2026 to November 20, 2026
BeamLuxor

Cost per DAX run

Beam

Per-second wall clock
$0.028per run
112.09s median at $0.9086/hr

$0.0000375/core-s (1 core = 2 vCPU, so 4 cores) + $0.0000064/GiB-s.

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 Beam 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.

Beam and Luxor were each faster in 1 of 2 shared sandbox benchmarks. In Burst TTI (November 20, 2026), Beam had a median time to interactive of 649ms versus 1.47s for Luxor, 2.26x faster. In DAX (November 20, 2026), Luxor had a median total workload time of 56.95s versus 112.09s for Beam, 1.97x faster.

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: Beam 100%, Luxor 100%; DAX: Beam 100%, Luxor 100%.

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