Browser Use vs Notte

Browser Benchmark Comparison · Updated October 30, 2026

Browser Use
Ahead in
2of 2 benchmarks
#4 of 7 in Browser Composite
vs
Notte
Ahead in
0of 2 benchmarks
#5 of 7 in Browser Composite

Browser Use was ahead in both shared browser benchmarks.

Head to head

  • Browser lifecycleTotal lifecycle time · lower is better
    Browser Use faster5.12x
    Browser Use
    0.33s
    Notte
    1.67s
  • Browser throughputActions per second · higher is better
    Browser Use higher throughput2.83x
    Browser Use
    3.76 actions/s
    Notte
    1.33 actions/s

Browser lifecycle

October 30, 2026
Full leaderboard

Browser Use

100% success
Median
0.33s
p95
0.39s
p99
0.41s
Browser Use Browser lifecycle results

Notte

100% success
Median
1.67s
p95
1.90s
p99
1.95s
Notte Browser lifecycle results

Median total lifecycle time over time

30 runs · June 30, 2026 to October 30, 2026
Browser UseNotte

Browser throughput

October 9, 2026
Full leaderboard

Browser Use

100% success
Median
3.76 actions/s
p95
4.89 actions/s
p99
5.11 actions/s
Browser Use Browser throughput results

Notte

100% success
Median
1.33 actions/s
p95
1.47 actions/s
p99
1.48 actions/s
Notte Browser throughput results

Median actions per second over time

22 runs · July 7, 2026 to October 30, 2026
Browser UseNotte
Work at Browser Use or Notte? 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 only when both providers completed at least 50% of runs in 2 or more shared benchmarks run in the last 30 days. 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 →Raw results on GitHub ↗

Frequently asked questions

Have another question? Email us.

Browser Use was ahead in both shared browser benchmarks. In Browser lifecycle (October 30, 2026), Browser Use had a median total lifecycle time of 0.33s versus 1.67s for Notte, 5.12x faster. In Browser throughput (October 9, 2026), Browser Use had a median actions per second of 3.76 actions/s versus 1.33 actions/s for Notte, 2.83x higher throughput.

PartnersGoogle Cloud Run