GPT-6 Astra
OpenAI · OpenCode 1.18.31 · guidance off
Rank 3 of 16 (tied)Verified · run and scored by the TimelineBench teamOpenCode 1.18.31guidance off
Resolution rate
21.4%[11.6, 34.4] exact 95% CI
12 of 56 tasks resolved, one attempt each
- Tests passed
- 48/56
- delivery + guards + must-haves
- Must-haves passed
- 49/56
- 87.5% [75.9, 94.8]
- Editors' win-or-tie
- 22.3%
- [14.8, 29.8] · 158 votes
- Rank · bootstrap interval
- 3 (tied) · 1.5–7
- by resolution rate, of 16 setups
- Videos delivered
- 53/56
- 3 missing
- Median runtime
- 26.2 min
- 39.4 h in total
- Auto Elo
- 783
- [662, 877] · pro cut 1000
- Editor Elo
- 752
- [667, 817]
- 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.
53pass · 94.6% - 02 / 04
Content guards
Silent, frozen, looped, dead air, one-sided sound, faces cut.
52still standing · 92.9% - 03 / 04
Brief must-haves
Every validated must-have of the brief.
48pass all tests · 85.7% - 04 / 04
Quality bar
Panel gap against the professional cut reaches the collection's tie margin.
12resolved · 21.4%
By collection
EditStock2/11resolved · 11/11 pass tests · bar 0.21
Cinestudy6/15resolved · 11/15 pass tests · bar 0.30
UGC1/15resolved · 14/15 pass tests · bar 1.54
Commercial3/15resolved · 12/15 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 · 2/11 resolved · tie margin 0.21 | ||||||
| Babiators | 4/4 | 6/6 | Pass · 12/15 items | +0.40 / 0.21 | Resolved | 0 · 0 · 3 |
| BOS Parkour | 4/4 | 6/6 | Pass · 9/9 items | −0.40 / 0.21 | Below bar | 0 · 0 · 3 |
| Evolve By Training Camp | 4/4 | 6/6 | Pass · 9/9 items | −0.37 / 0.21 | Below bar | 2 · 0 · 1 |
| Incubate | 4/4 | 6/6 | Pass · 12/15 items | +0.02 / 0.21 | Below bar | 0 · 0 · 3 |
| J-Pops | 4/4 | 6/6 | Pass · 13/15 items | −0.05 / 0.21 | Below bar | 0 · 0 · 3 |
| Klug Fitness Brand Story | 4/4 | 6/6 | Pass · 15/15 items | +0.65 / 0.21 | Resolved | 1 · 0 · 2 |
| Klug Fitness Next Time | 4/4 | 6/6 | Pass · 14/15 items | +0.12 / 0.21 | Below bar | 0 · 0 · 3 |
| Klug Fitness Railroad Track | 4/4 | 6/6 | Pass · 15/15 items | +0.12 / 0.21 | Below bar | 0 · 0 · 3 |
| Two Player | 4/4 | 6/6 | Pass · 9/15 items | −0.63 / 0.21 | Below bar | 1 · 1 · 1 |
| Whisper Fan | 4/4 | 6/6 | Pass · 7/7 items | −0.08 / 0.21 | Below bar | 1 · 0 · 2 |
| Wild Planet | 4/4 | 6/6 | Pass · 7/8 items | 0.00 / 0.21 | Below bar | 0 · 1 · 2 |
| Cinestudy · 6/15 resolved · tie margin 0.30 | ||||||
| Car Chase | No output · time limit | — | — | — | No output | — |
| Color Grading | No output · time limit | — | — | — | No output | — |
| Compression Of Time | 4/4 | Mostly frozen | Pass · 15/15 items | −0.53 / 0.30 | Failed a test | 0 · 1 · 1 |
| Cutting On Motion | 4/4 | 6/6 | Pass · 10/14 items | −0.18 / 0.30 | Below bar | 2 · 0 · 1 |
| Documentary Format | 4/4 | 6/6 | Pass · 13/15 items | +0.31 / 0.30 | Resolved | 1 · 0 · 2 |
| Editing A Sequence | 4/4 | 6/6 | Pass · 14/15 items | +1.81 / 0.30 | Resolved | 2 · 0 · 1 |
| Horror Movie | 4/4 | 6/6 | Pass · 14/15 items | +0.50 / 0.30 | Resolved | 0 · 0 · 3 |
| Hospital Scene | 4/4 | 6/6 | Pass · 14/15 items | +0.07 / 0.30 | Below bar | 0 · 0 · 3 |
| License Exam | 4/4 | 6/6 | Pass · 15/15 items | +0.72 / 0.30 | Resolved | 0 · 1 · 2 |
| Movie Trailer | 4/4 | 6/6 | Pass · 13/15 items | +0.68 / 0.30 | Resolved | 1 · 1 · 1 |
| Podcast Documentary | 4/4 | 6/6 | Pass · 13/15 items | +0.16 / 0.30 | Below bar | 2 · 0 · 1 |
| Refractory | 4/4 | 6/6 | Pass · 14/15 items | +0.95 / 0.30 | Resolved | 2 · 0 · 1 |
| Relationship Card | 4/4 | 6/6 | Fail · 14/15 items | +0.58 / 0.30 | Failed a test | 0 · 1 · 2 |
| Restaurant Scene | 4/4 | 6/6 | Pass · 10/15 items | −0.54 / 0.30 | Below bar | 0 · 1 · 2 |
| The Intern Mockumentary | 4/4 | 6/6 | Pass · 14/14 items | −0.60 / 0.30 | Below bar | 1 · 0 · 2 |
| UGC · 1/15 resolved · tie margin 1.54 | ||||||
| Breathex Nose Patches | 4/4 | 6/6 | Pass · 12/15 items | +0.36 / 1.54 | Below bar | 0 · 0 · 3 |
| CUPNEX | 4/4 | 6/6 | Pass · 12/15 items | +0.68 / 1.54 | Below bar | 0 · 0 · 3 |
| Dazzle and Charm | 4/4 | 6/6 | Pass · 13/15 items | +1.68 / 1.54 | Resolved | 0 · 1 · 2 |
| Feel Comfy | 4/4 | 6/6 | Pass · 12/14 items | +0.41 / 1.54 | Below bar | 0 · 0 · 3 |
| Fitness Venue | 4/4 | 6/6 | Pass · 13/15 items | +0.61 / 1.54 | Below bar | 0 · 0 · 3 |
| Global Physiotherapy Clinic | 4/4 | 6/6 | Pass · 13/15 items | +0.91 / 1.54 | Below bar | 0 · 0 · 3 |
| House of Hue | 4/4 | 6/6 | Pass · 10/15 items | +0.70 / 1.54 | Below bar | 1 · 1 · 1 |
| LeadLoop | 4/4 | 6/6 | Fail · 10/15 items | +0.54 / 1.54 | Failed a test | 0 · 0 · 3 |
| LedgeFin | 4/4 | 6/6 | Pass · 12/15 items | +0.93 / 1.54 | Below bar | 0 · 0 · 3 |
| MotionMix Studio | 4/4 | 6/6 | Pass · 14/15 items | +0.68 / 1.54 | Below bar | 0 · 0 · 3 |
| Nova Sole | 4/4 | 6/6 | Pass · 13/15 items | −0.17 / 1.54 | Below bar | 0 · 0 · 3 |
| Off Case | 4/4 | 6/6 | Pass · 13/15 items | +0.03 / 1.54 | Below bar | 0 · 0 · 3 |
| Personal Branding | 4/4 | 6/6 | Pass · 11/15 items | +0.19 / 1.54 | Below bar | 0 · 0 · 3 |
| Personal Introduction | 4/4 | 6/6 | Pass · 14/15 items | +1.47 / 1.54 | Below bar | 0 · 0 · 3 |
| Portable Side Bag | 4/4 | 6/6 | Pass · 12/15 items | +0.81 / 1.54 | Below bar | 0 · 0 · 3 |
| Commercial · 3/15 resolved · tie margin 0.52 | ||||||
| Aroma Candle | 4/4 | 6/6 | Pass · 14/15 items | +0.04 / 0.52 | Below bar | 0 · 0 · 3 |
| Bean & Roast | 4/4 | 6/6 | Fail · 14/15 items | +0.53 / 0.52 | Failed a test | 0 · 0 · 3 |
| Beauty of Delhi | 4/4 | 6/6 | Pass · 13/15 items | +0.96 / 0.52 | Resolved | 0 · 0 · 3 |
| Bike Ride | 4/4 | 6/6 | Pass · 15/15 items | +0.87 / 0.52 | Resolved | 1 · 0 · 2 |
| Camera | 4/4 | 6/6 | Fail · 12/15 items | −0.16 / 0.52 | Failed a test | 1 · 0 · 2 |
| Fortunex | 4/4 | 6/6 | Pass · 13/15 items | −0.38 / 0.52 | Below bar | 2 · 0 · 1 |
| Hard Life Of Athlete | 4/4 | 6/6 | Pass · 11/15 items | −0.50 / 0.52 | Below bar | 0 · 0 · 3 |
| Loom Craft | 4/4 | 6/6 | Pass · 14/15 items | +0.03 / 0.52 | Below bar | 1 · 0 · 2 |
| Motionmix In Charge | 4/4 | 6/6 | Pass · 13/13 items | +0.90 / 0.52 | Resolved | 0 · 0 · 3 |
| Pro Bite | 4/4 | 6/6 | Pass · 9/15 items | +0.47 / 0.52 | Below bar | 1 · 0 · 2 |
| Quickshine | 4/4 | 6/6 | Pass · 9/14 items | −0.43 / 0.52 | Below bar | 0 · 0 · 3 |
| Shadow Airpod | No output · time limit | — | — | — | No output | — |
| Standcup | 4/4 | 6/6 | Pass · 12/15 items | −0.07 / 0.52 | Below bar | 2 · 0 · 1 |
| Street Wear | 4/4 | 6/6 | Pass · 15/15 items | −0.21 / 0.52 | Below bar | 0 · 0 · 3 |
| Voltix Bulb | 4/4 | 6/6 | Pass · 13/15 items | 0.00 / 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
- Hit the 300-minute CLI budget3
Car Chase, Color Grading, Shadow Airpod
Delivery failures
Every delivered video passes its four delivery tests.
Guard failures
- Mostly frozen1
Reproduce
Run this setup
# GPT-6 Astra · OpenCode 1.18.31 · guidance off
# source packs are not distributed; the maintainers run the agent internally
harbor run -p tasks/<id> -a opencode -m openai/gpt-6-astra
# after all 56 tasks, one attempt each:
timelinebench aggregate <jobs-dir>Setup id opencode__gpt-6-astra__skills-off · model openai/gpt-6-astra · run guide
Disclosures
- One run per task.
- The reference edits are professional edits, not certified ground truth.