Overall Sandbox Composite Score
Each provider's score averaged across every sandbox benchmark over the previous 7 days.
LightningAI
| Benchmark | | ||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Composite score | 89.78 | 86.72 | 83.35 | 75.21 | 69.64 | 69.06 | 67.36 | 67.32 | 66.83 | 60.40 | 58.34 | 57.82 | 57.10 | 54.96 | 54.74 | 52.08 | 50.49 | 48.80 | 46.31 | 43.02 | 42.60 | 41.26 | 39.78 | 38.44 | 35.44 | 33.34 | 31.43 | 31.13 | 31.11 | 30.54 | 27.87 | 23.65 | 10.37 | 1.86 | 1.79 | 1.79 | 1.79 |
| Sandbox Burst Survival - Stealth | 99.95 | 99.96 | 99.79 | 99.95 | 99.81 | 99.85 | 99.96 | 99.91 | 99.88 | 87.53 | 99.88 | 100.00 | 99.79 | 99.89 | 100.00 | 77.86 | 98.75 | 99.87 | 99.96 | 99.87 | 99.98 | 99.11 | 51.42 | 99.95 | 99.56 | 45.23 | 99.84 | 97.61 | 99.99 | 97.88 | 99.63 | 51.07 | 39.09 | 15.00 | 15.00 | 15.00 | 15.00 |
| Sandbox CPU Burst - Stealth | 47.60 | — | 40.04 | 31.96 | 46.68 | — | 21.11 | — | 68.79 | 51.40 | 39.81 | 0.00 | — | 39.28 | 37.72 | 28.80 | 20.90 | — | — | 28.04 | 20.28 | 32.75 | — | 73.55 | 25.84 | 66.51 | 20.95 | 44.19 | 0.00 | 30.30 | 27.04 | 33.32 | — | 0.00 | 0.00 | 0.00 | 0.00 |
| Sandbox Dax - Daily | 79.04 | 88.55 | 68.08 | 67.06 | 58.34 | 56.24 | 75.98 | — | 68.24 | 75.80 | 75.37 | 69.59 | 0.00 | 81.76 | 64.58 | 0.00 | 78.08 | 0.00 | — | 51.38 | 61.01 | 82.66 | 32.45 | 68.16 | 51.60 | 0.00 | 0.00 | 0.00 | 88.85 | 0.00 | 52.42 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Sandbox Fidelity - Stealth | 99.55 | 0.00 | 98.04 | 95.91 | 94.75 | 19.48 | 94.77 | 98.58 | 92.76 | 0.00 | 0.00 | 0.00 | 85.19 | 0.00 | 0.00 | 78.38 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 15.47 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Sandbox Filesystem API Throughput - Stealth | 100.00 | — | 62.31 | 100.00 | 62.67 | — | 51.09 | — | 100.00 | 61.43 | 32.00 | 14.60 | — | 8.00 | 85.00 | 62.26 | 8.00 | — | — | 17.79 | 2.00 | 1.89 | — | 8.00 | 0.00 | 70.65 | 0.00 | 31.71 | 0.00 | 1.89 | 19.14 | 1.96 | — | 0.00 | 0.00 | 0.00 | 0.00 |
| Sandbox FS I/O - Stealth | 96.77 | — | 93.99 | 97.10 | 0.00 | — | 95.72 | — | 0.00 | 96.18 | 96.05 | 66.16 | — | 96.07 | 97.34 | 83.05 | 69.07 | — | — | 88.91 | 95.82 | 95.90 | — | 5.51 | 98.12 | 92.67 | 84.33 | 0.00 | 0.00 | 0.00 | 44.41 | 48.61 | — | 0.00 | 0.00 | 0.00 | 0.00 |
| Sandbox Pause Resume - Stealth | 94.81 | 99.71 | 97.52 | 0.00 | 98.67 | 99.44 | 0.00 | 0.00 | 0.00 | 97.80 | 94.19 | 99.94 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 42.80 | 0.00 | 0.00 | 0.00 | 0.00 | 87.23 | 0.00 | 92.63 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Sandbox Snapshot - Stealth | 99.62 | 0.00 | 98.12 | 99.27 | 98.18 | 19.34 | 92.75 | 98.61 | 99.59 | 0.00 | 0.00 | 83.04 | 98.92 | 98.65 | 0.00 | 78.38 | 93.76 | 98.75 | 79.38 | 0.00 | 0.00 | 0.00 | 19.90 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 31.79 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Sandbox TTI (Burst) - Daily | 92.83 | 97.65 | 95.48 | 94.98 | 79.95 | 80.54 | 92.54 | — | 90.59 | 61.19 | 74.50 | 98.28 | 61.64 | 73.50 | 93.48 | 62.95 | 89.32 | 94.51 | — | 89.45 | 95.81 | 58.40 | 41.32 | 88.13 | 37.99 | 4.77 | 58.27 | 0.32 | 99.10 | 0.00 | 8.55 | 55.30 | 13.83 | 0.00 | 0.00 | 0.00 | 0.00 |
Methodology
This page is a meta-benchmark: it never starts a sandbox. It reads the daily composite scores every sandbox benchmark already published and averages them into one weekly number per provider. For the scores behind each row see the individual Sandbox Benchmarks.
How the Weekly Composite Is Built
The window is the previous 7 complete UTC days. Each provider's score is averaged in three steps:
- Per benchmark, per day — average the composite score across all of that benchmark's runs that day, so re-runs are folded in rather than cherry-picked.
- Per day — average those numbers across every sandbox benchmark that scored the provider that day.
- Per week — average the daily composites across the days that had data. That is the weekly composite shown on each card and in the Composite score row.
Missing Data
Missing data is skipped, never zeroed. A benchmark with no runs on a given day doesn't count toward that day, and a day with no scores doesn't count toward the week.
Each matrix cell is that benchmark's average across the days it scored the provider; hover a cell to see how many days of the window it covers. A — means the provider has no score for that benchmark this week.