GPT-6 Astra
OpenAI · Codex computer use native Computer Use · guidance off · computer use
Rank 14 of 16 (tied)Verified · run and scored by the TimelineBench teamCodex computer use native Computer Useguidance offcomputer use
Resolution rate
3.6%[0.4, 12.3] exact 95% CI
2 of 56 tasks resolved, one attempt each
- Tests passed
- 35/56
- delivery + guards + must-haves
- Must-haves passed
- 43/56
- 76.8% [63.6, 87.0]
- Editors' win-or-tie
- 8.2%
- [3.0, 13.3] · 159 votes
- Rank · bootstrap interval
- 14 (tied) · 12–15.5
- by resolution rate, of 16 setups
- Videos delivered
- 53/56
- 3 missing
- Median runtime
- 52.7 min
- 51.7 h in total
- Auto Elo
- 376
- [182, 554] · pro cut 1000
- Editor Elo
- 511
- [354, 597]
- Cost
- Not recorded
- recorded for Claude Code only
- 01 / 04
Delivery tests
53 videos delivered; the four tests of each task's tests/test.sh.
51pass · 91.1% - 02 / 04
Content guards
Silent, frozen, looped, dead air, one-sided sound, faces cut.
44still standing · 78.6% - 03 / 04
Brief must-haves
Every validated must-have of the brief.
35pass all tests · 62.5% - 04 / 04
Quality bar
Panel gap against the professional cut reaches the collection's tie margin.
2resolved · 3.6%
By collection
EditStock0/11resolved · 8/11 pass tests · bar 0.21
Cinestudy2/15resolved · 8/15 pass tests · bar 0.30
UGC0/15resolved · 8/15 pass tests · bar 1.54
Commercial0/15resolved · 11/15 pass tests · bar 0.52
Per task
first failing layer, panel gap and editor votes| Task | Delivery | Guards | Must-haves | Gap vs bar | Outcome | Editors A·T·P |
|---|---|---|---|---|---|---|
| EditStock · 0/11 resolved · tie margin 0.21 | ||||||
| Babiators | 4/4 | 6/6 | Pass · 12/15 items | −0.68 / 0.21 | Below bar | 0 · 1 · 2 |
| BOS Parkour | 4/4 | 6/6 | Pass · 9/9 items | −1.63 / 0.21 | Below bar | 0 · 0 · 3 |
| Evolve By Training Camp | 4/4 | 6/6 | Fail · 8/9 items | −2.83 / 0.21 | Failed a test | 0 · 0 · 3 |
| Incubate | 4/4 | 6/6 | Pass · 10/15 items | −1.54 / 0.21 | Below bar | 1 · 0 · 2 |
| J-Pops | 4/4 | 6/6 | Pass · 13/15 items | −0.84 / 0.21 | Below bar | 0 · 0 · 3 |
| Klug Fitness Brand Story | No output · gave up | — | — | — | No output | — |
| Klug Fitness Next Time | 4/4 | 6/6 | Pass · 13/15 items | −1.26 / 0.21 | Below bar | 0 · 0 · 3 |
| Klug Fitness Railroad Track | 3/4 · video | 6/6 | Pass · 15/15 items | −1.35 / 0.21 | Failed a test | 0 · 0 · 3 |
| Two Player | 4/4 | 6/6 | Pass · 8/15 items | −1.97 / 0.21 | Below bar | 0 · 0 · 3 |
| Whisper Fan | 4/4 | 6/6 | Pass · 7/7 items | +0.03 / 0.21 | Below bar | 0 · 0 · 3 |
| Wild Planet | 4/4 | 6/6 | Pass · 7/8 items | −0.93 / 0.21 | Below bar | 0 · 0 · 3 |
| Cinestudy · 2/15 resolved · tie margin 0.30 | ||||||
| Car Chase | 4/4 | 6/6 | Pass · 13/13 items | −0.34 / 0.30 | Below bar | 0 · 0 · 3 |
| Color Grading | 4/4 | 6/6 | Pass · 14/15 items | +0.08 / 0.30 | Below bar | 1 · 0 · 2 |
| Compression Of Time | 4/4 | Mostly frozen | Pass · 15/15 items | −1.07 / 0.30 | Failed a test | 0 · 0 · 3 |
| Cutting On Motion | 4/4 | Mostly frozen | Pass · 10/14 items | −0.98 / 0.30 | Failed a test | 0 · 1 · 2 |
| Documentary Format | No output · gave up | — | — | — | No output | — |
| Editing A Sequence | 4/4 | 6/6 | Pass · 13/15 items | +0.68 / 0.30 | Resolved | 1 · 1 · 1 |
| Horror Movie | 4/4 | Mostly silent, Dead air | Pass · 14/15 items | −0.70 / 0.30 | Failed a test | 0 · 0 · 3 |
| Hospital Scene | 4/4 | 6/6 | Pass · 11/15 items | −0.43 / 0.30 | Below bar | 0 · 0 · 3 |
| License Exam | 4/4 | 6/6 | Pass · 14/15 items | −2.52 / 0.30 | Below bar | 0 · 0 · 3 |
| Movie Trailer | 4/4 | 6/6 | Pass · 13/15 items | +0.38 / 0.30 | Resolved | 1 · 0 · 2 |
| Podcast Documentary | No output · gave up | — | — | — | No output | — |
| Refractory | 4/4 | 6/6 | Fail · 13/15 items | −1.14 / 0.30 | Failed a test | 0 · 0 · 3 |
| Relationship Card | 4/4 | 6/6 | Pass · 11/15 items | −1.16 / 0.30 | Below bar | 0 · 0 · 3 |
| Restaurant Scene | 4/4 | 6/6 | Pass · 11/15 items | −0.74 / 0.30 | Below bar | 0 · 0 · 3 |
| The Intern Mockumentary | 4/4 | Repeated footage, Dead air | Pass · 9/14 items | −1.67 / 0.30 | Failed a test | 0 · 0 · 3 |
| UGC · 0/15 resolved · tie margin 1.54 | ||||||
| Breathex Nose Patches | 4/4 | 6/6 | Fail · 7/15 items | −1.00 / 1.54 | Failed a test | 0 · 0 · 3 |
| CUPNEX | 4/4 | 6/6 | Pass · 8/15 items | −1.83 / 1.54 | Below bar | 0 · 0 · 3 |
| Dazzle and Charm | 4/4 | 6/6 | Fail · 8/15 items | +0.79 / 1.54 | Failed a test | 0 · 0 · 3 |
| Feel Comfy | 4/4 | 6/6 | Pass · 8/14 items | −0.72 / 1.54 | Below bar | 0 · 0 · 3 |
| Fitness Venue | 4/4 | 6/6 | Pass · 12/15 items | +0.59 / 1.54 | Below bar | 0 · 1 · 2 |
| Global Physiotherapy Clinic | 4/4 | 6/6 | Pass · 13/15 items | +0.63 / 1.54 | Below bar | 0 · 0 · 3 |
| House of Hue | 4/4 | 6/6 | Pass · 8/15 items | −0.46 / 1.54 | Below bar | 0 · 0 · 3 |
| LeadLoop | 4/4 | 6/6 | Fail · 8/15 items | −0.08 / 1.54 | Failed a test | 0 · 0 · 3 |
| LedgeFin | 4/4 | 6/6 | Fail · 9/15 items | −0.51 / 1.54 | Failed a test | 0 · 0 · 3 |
| MotionMix Studio | 4/4 | 6/6 | Pass · 13/15 items | +0.08 / 1.54 | Below bar | 0 · 0 · 3 |
| Nova Sole | 4/4 | 6/6 | Pass · 12/15 items | −0.21 / 1.54 | Below bar | 0 · 0 · 3 |
| Off Case | 4/4 | 6/6 | Fail · 9/15 items | −1.00 / 1.54 | Failed a test | 0 · 0 · 3 |
| Personal Branding | 4/4 | 6/6 | Pass · 10/15 items | −0.41 / 1.54 | Below bar | 0 · 0 · 3 |
| Personal Introduction | 4/4 | 6/6 | Fail · 9/15 items | +0.41 / 1.54 | Failed a test | 0 · 1 · 2 |
| Portable Side Bag | 4/4 | 6/6 | Fail · 9/15 items | −0.03 / 1.54 | Failed a test | 0 · 0 · 3 |
| Commercial · 0/15 resolved · tie margin 0.52 | ||||||
| Aroma Candle | 4/4 | 6/6 | Pass · 13/15 items | −0.73 / 0.52 | Below bar | 0 · 0 · 3 |
| Bean & Roast | 4/4 | 6/6 | Pass · 15/15 items | −0.03 / 0.52 | Below bar | 0 · 1 · 2 |
| Beauty of Delhi | 4/4 | Mostly frozen, Repeated footage | Pass · 12/15 items | +0.42 / 0.52 | Failed a test | 0 · 0 · 3 |
| Bike Ride | 3/4 · duration | 6/6 | Fail · 1/15 items | −1.86 / 0.52 | Failed a test | 0 · 1 · 2 |
| Camera | 4/4 | Mostly silent, Dead air | Pass · 13/15 items | −1.11 / 0.52 | Failed a test | 0 · 0 · 3 |
| Fortunex | 4/4 | 6/6 | Pass · 13/15 items | −0.78 / 0.52 | Below bar | 0 · 0 · 3 |
| Hard Life Of Athlete | 4/4 | 6/6 | Pass · 12/15 items | −0.57 / 0.52 | Below bar | 0 · 0 · 3 |
| Loom Craft | 4/4 | 6/6 | Pass · 12/15 items | −1.57 / 0.52 | Below bar | 0 · 1 · 2 |
| Motionmix In Charge | 4/4 | 6/6 | Pass · 12/13 items | +0.29 / 0.52 | Below bar | 0 · 0 · 3 |
| Pro Bite | 4/4 | 6/6 | Pass · 10/15 items | −0.01 / 0.52 | Below bar | 0 · 0 · 3 |
| Quickshine | 4/4 | 6/6 | Pass · 7/14 items | −1.07 / 0.52 | Below bar | 0 · 0 · 3 |
| Shadow Airpod | 4/4 | 6/6 | Pass · 14/15 items | +0.32 / 0.52 | Below bar | 0 · 0 · 3 |
| Standcup | 4/4 | 6/6 | Pass · 11/15 items | −1.12 / 0.52 | Below bar | 0 · 0 · 3 |
| Street Wear | 4/4 | One-sided sound | Pass · 13/15 items | −1.38 / 0.52 | Failed a test | 0 · 0 · 3 |
| Voltix Bulb | 4/4 | 6/6 | Pass · 14/15 items | −0.02 / 0.52 | Below bar | 1 · 0 · 2 |
ResolvedPassed tests, below barFailed a testNo outputEditors A·T·P: blind votes for the agent cut, a tie, or the professional cut.
Missing outputs
- Agent gave up and declared the cut incomplete3
Podcast Documentary, Documentary Format, Klug Fitness Brand Story
Delivery failures
- video1
- duration1
Guard failures
- Dead air3
- Mostly frozen3
- Mostly silent2
- Repeated footage2
- One-sided sound1
Reproduce
Codex's native Computer Use driving DaVinci Resolve on macOS. It is not a Harbor agent, so this entry cannot be re-run with harbor run.
Setup id cua-codex__gpt-6-astra__skills-off · model gpt-6-astra · run guide
Disclosures
- One run per task.
- The reference edits are professional edits, not certified ground truth.