Accuracy
Measurements are only worth something if you can check them. Here is how Bolts is tested, and the whole run underneath.
- 96% of tricks identified correctly
- 99% of flights tracked without losing the board
- 8ms typical phase timing error
- 99% of airborne frames with both feet tracked
Product targets. The engineering benchmark below is the current build measured against them, in full and including what it misses.
How it is tested
There is a set of 2134 skate clips that people have gone through by hand, marking the trick and the frame each moment happened on.
Bolts never sees most of them while it is being built. Every score below comes from 125 clips it has never been shown — the same idea as sitting an exam on questions you did not revise from. No figure on this site is typed in; each one is read out of a saved run when the site is built.
Why slow motion is not optional
The test clips are a mix — 85 filmed at 30 frames a second, 39 at 120 — so the effect of frame rate can be measured rather than asserted.
Counting in frames flatters the slower footage: two frames is a long moment at 30 a second and a short one at 120. Judged in thousandths of a second, which is the like-for-like comparison, the slow-motion footage wins on every moment.
| Moment | 480p30, within 2 frames | 1080p120, within 2 frames | 480p30, within 33ms | 1080p120, within 33ms |
|---|---|---|---|---|
| takeoff | 89% | 49% | 63% | 77% |
| peak | 71% | 37% | 43% | 66% |
| land | 76% | 31% | 48% | 54% |
The two greyed columns are the misleading reading; the right-hand pair is the fair one. The peak is the clearest case — it happens between two frames, so a slower camera cannot catch it however good the software is.
The benchmark, in full
Targets written down before the work started, so they could not be moved afterwards. This is the current state against them, misses included. Right now 2 of 7 are met.
Open the full run 7 gates, 2 met
| Gate | Bar | Measured | Clips | Result |
|---|---|---|---|---|
| Keeps track of your feet in the air Can it follow your feet while you are off the ground? | ≥ 95% | 99% | 124 | clears |
| Picks the right frame for takeoff Does it agree with a person about when you left the ground? | ≥ 85% | 76% | 124 | misses |
| Picks the right frame for landing Same question for coming back down. | ≥ 85% | 61% | 124 | misses |
| Stays locked on your board Does it follow your board the whole way, instead of wandering onto something else? | ≤ 5% | 6% | 51 | misses |
| Counts the flips right How many times the board rolled over, exactly. | ≥ 90% | 100% | 10 | clears |
| Gets the whole trick right Flip, board spin, your spin and stance — all four at once, or it counts as wrong. | ≥ 90% | 22% | 125 | misses |
| Knows if you rode away Did you land it, or did you bail? | ≥ 90% | 82% | 125 | misses |
Why the whole-trick number is the hard one
Getting the trick right means getting four things right at once — flip, board spin, your spin, stance — and missing any one counts the whole thing wrong. Taken separately the parts score far better than the total. We report the strict version because the generous version would look better and tell you less.
One target we do not score
There is a gate about how well the box around the board lines up. We record the typical overlap rather than the share of frames clearing the line, and the typical value cannot answer that question — so it is absent rather than answered with a number nothing measured.
Test split 125 clips, 0 errors, setup m4_audio_profile, code ae5683e-dirty, run 2026-09-12. Run id 20260912T073233142996_m4_audio_profile_test.
See it on your own tricks
Film one and check the numbers yourself.