DeepSeek Flash
DeepSeek · OpenCode 1.18.31 · guidance off
Rank 13 of 16Verified · run and scored by the TimelineBench teamOpenCode 1.18.31guidance off
Resolution rate
7.1%[2.0, 17.3] exact 95% CI
4 of 56 tasks resolved, one attempt each
- Tests passed
- 43/56
- delivery + guards + must-haves
- Must-haves passed
- 48/56
- 85.7% [73.8, 93.6]
- Editors' win-or-tie
- 13.0%
- [6.9, 19.2] · 164 votes
- Rank · bootstrap interval
- 13 · 10–15
- by resolution rate, of 16 setups
- Videos delivered
- 55/56
- 1 missing
- Median runtime
- 33.5 min
- 33.7 h in total
- Auto Elo
- 554
- [304, 689] · pro cut 1000
- Editor Elo
- 624
- [500, 703]
- Cost
- Not recorded
- recorded for Claude Code only
- 01 / 04
Delivery tests
55 videos delivered; the four tests of each task's tests/test.sh.
55pass · 98.2% - 02 / 04
Content guards
Silent, frozen, looped, dead air, one-sided sound, faces cut.
49still standing · 87.5% - 03 / 04
Brief must-haves
Every validated must-have of the brief.
43pass all tests · 76.8% - 04 / 04
Quality bar
Panel gap against the professional cut reaches the collection's tie margin.
4resolved · 7.1%
By collection
EditStock1/11resolved · 8/11 pass tests · bar 0.21
Cinestudy1/15resolved · 12/15 pass tests · bar 0.30
UGC1/15resolved · 10/15 pass tests · bar 1.54
Commercial1/15resolved · 13/15 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 · 1/11 resolved · tie margin 0.21 | ||||||
| Babiators | 4/4 | 6/6 | Pass · 13/15 items | −0.64 / 0.21 | Below bar | 0 · 0 · 3 |
| BOS Parkour | 4/4 | Repeated footage | Pass · 9/9 items | −1.24 / 0.21 | Failed a test | 0 · 0 · 3 |
| Evolve By Training Camp | 4/4 | 6/6 | Pass · 7/9 items | −1.61 / 0.21 | Below bar | 0 · 1 · 2 |
| Incubate | 4/4 | 6/6 | Fail · 9/15 items | −0.83 / 0.21 | Failed a test | 0 · 0 · 3 |
| J-Pops | 4/4 | 6/6 | Pass · 11/15 items | −2.80 / 0.21 | Below bar | 0 · 0 · 3 |
| Klug Fitness Brand Story | 4/4 | 6/6 | Pass · 15/15 items | +0.36 / 0.21 | Resolved | 0 · 0 · 3 |
| Klug Fitness Next Time | 4/4 | 6/6 | Pass · 13/15 items | −0.46 / 0.21 | Below bar | 0 · 0 · 3 |
| Klug Fitness Railroad Track | 4/4 | 6/6 | Pass · 15/15 items | −0.29 / 0.21 | Below bar | 0 · 0 · 3 |
| Two Player | 4/4 | 6/6 | Pass · 8/15 items | −1.23 / 0.21 | Below bar | 0 · 0 · 3 |
| Whisper Fan | 4/4 | 6/6 | Pass · 7/7 items | +0.03 / 0.21 | Below bar | 1 · 0 · 1 |
| Wild Planet | 4/4 | One-sided sound | Pass · 7/8 items | −0.68 / 0.21 | Failed a test | 0 · 0 · 3 |
| Cinestudy · 1/15 resolved · tie margin 0.30 | ||||||
| Car Chase | 4/4 | 6/6 | Pass · 13/13 items | −0.57 / 0.30 | Below bar | 0 · 0 · 3 |
| Color Grading | 4/4 | 6/6 | Pass · 11/15 items | +0.21 / 0.30 | Below bar | 1 · 1 · 1 |
| Compression Of Time | 4/4 | 6/6 | Pass · 15/15 items | −0.79 / 0.30 | Below bar | 0 · 1 · 2 |
| Cutting On Motion | 4/4 | 6/6 | Pass · 9/14 items | −1.10 / 0.30 | Below bar | 0 · 0 · 3 |
| Documentary Format | 4/4 | 6/6 | Pass · 12/15 items | +0.25 / 0.30 | Below bar | 0 · 0 · 3 |
| Editing A Sequence | 4/4 | 6/6 | Fail · 11/15 items | +1.18 / 0.30 | Failed a test | 2 · 1 · 0 |
| Horror Movie | 4/4 | 6/6 | Pass · 12/15 items | −1.36 / 0.30 | Below bar | 1 · 0 · 2 |
| Hospital Scene | 4/4 | 6/6 | Pass · 13/15 items | −0.21 / 0.30 | Below bar | 1 · 1 · 1 |
| License Exam | 4/4 | 6/6 | Fail · 13/15 items | −1.47 / 0.30 | Failed a test | 0 · 0 · 3 |
| Movie Trailer | 4/4 | 6/6 | Pass · 13/15 items | +0.41 / 0.30 | Resolved | 0 · 0 · 3 |
| Podcast Documentary | 4/4 | 6/6 | Pass · 13/15 items | −1.30 / 0.30 | Below bar | 0 · 0 · 3 |
| Refractory | 4/4 | 6/6 | Pass · 14/15 items | −0.22 / 0.30 | Below bar | 1 · 1 · 1 |
| Relationship Card | 4/4 | Dead air | Fail · 13/15 items | −1.02 / 0.30 | Failed a test | 0 · 0 · 3 |
| Restaurant Scene | 4/4 | 6/6 | Pass · 12/15 items | −0.23 / 0.30 | Below bar | 1 · 0 · 2 |
| The Intern Mockumentary | 4/4 | 6/6 | Pass · 14/14 items | −0.46 / 0.30 | Below bar | 0 · 1 · 2 |
| UGC · 1/15 resolved · tie margin 1.54 | ||||||
| Breathex Nose Patches | 4/4 | 6/6 | Pass · 11/15 items | −0.35 / 1.54 | Below bar | 0 · 1 · 2 |
| CUPNEX | 4/4 | 6/6 | Pass · 12/15 items | +1.00 / 1.54 | Below bar | 0 · 0 · 3 |
| Dazzle and Charm | 4/4 | 6/6 | Pass · 11/15 items | +1.58 / 1.54 | Resolved | 0 · 0 · 3 |
| Feel Comfy | 4/4 | 6/6 | Pass · 11/14 items | +0.05 / 1.54 | Below bar | 0 · 0 · 3 |
| Fitness Venue | 4/4 | 6/6 | Pass · 13/15 items | +0.55 / 1.54 | Below bar | 1 · 0 · 2 |
| Global Physiotherapy Clinic | 4/4 | Faces cut by the frame | Pass · 10/15 items | −0.30 / 1.54 | Failed a test | 0 · 0 · 3 |
| House of Hue | 4/4 | 6/6 | Pass · 9/15 items | +0.19 / 1.54 | Below bar | 0 · 0 · 3 |
| LeadLoop | 4/4 | 6/6 | Fail · 11/15 items | +0.17 / 1.54 | Failed a test | 1 · 0 · 2 |
| LedgeFin | 4/4 | 6/6 | Pass · 13/15 items | +0.63 / 1.54 | Below bar | 0 · 0 · 3 |
| MotionMix Studio | 4/4 | 6/6 | Pass · 13/15 items | −0.55 / 1.54 | Below bar | 0 · 0 · 3 |
| Nova Sole | 4/4 | Repeated footage | Pass · 13/15 items | −0.34 / 1.54 | Failed a test | 0 · 0 · 3 |
| Off Case | No output · stopped early | — | — | — | No output | — |
| Personal Branding | 4/4 | 6/6 | Pass · 12/15 items | 0.00 / 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 | Faces cut by the frame | Pass · 12/15 items | −0.38 / 1.54 | Failed a test | 0 · 0 · 3 |
| Commercial · 1/15 resolved · tie margin 0.52 | ||||||
| Aroma Candle | 4/4 | 6/6 | Fail · 11/15 items | +0.05 / 0.52 | Failed a test | 0 · 0 · 3 |
| Bean & Roast | 4/4 | 6/6 | Pass · 15/15 items | −0.37 / 0.52 | Below bar | 1 · 1 · 1 |
| Beauty of Delhi | 4/4 | 6/6 | Pass · 12/15 items | +0.67 / 0.52 | Resolved | 0 · 0 · 3 |
| Bike Ride | 4/4 | 6/6 | Pass · 14/15 items | +0.42 / 0.52 | Below bar | 0 · 0 · 3 |
| Camera | 4/4 | 6/6 | Pass · 13/15 items | −1.10 / 0.52 | Below bar | 0 · 0 · 3 |
| Fortunex | 4/4 | 6/6 | Pass · 12/15 items | −0.17 / 0.52 | Below bar | 0 · 0 · 3 |
| Hard Life Of Athlete | 4/4 | 6/6 | Pass · 11/15 items | −0.40 / 0.52 | Below bar | 0 · 0 · 3 |
| Loom Craft | 4/4 | 6/6 | Fail · 10/15 items | −1.45 / 0.52 | Failed a test | 0 · 0 · 3 |
| Motionmix In Charge | 4/4 | 6/6 | Pass · 12/13 items | +0.35 / 0.52 | Below bar | 0 · 0 · 3 |
| Pro Bite | 4/4 | 6/6 | Pass · 12/15 items | 0.00 / 0.52 | Below bar | 0 · 0 · 3 |
| Quickshine | 4/4 | 6/6 | Pass · 10/14 items | −0.82 / 0.52 | Below bar | 0 · 0 · 3 |
| Shadow Airpod | 4/4 | 6/6 | Pass · 12/15 items | −0.27 / 0.52 | Below bar | 0 · 0 · 3 |
| Standcup | 4/4 | 6/6 | Pass · 12/15 items | +0.09 / 0.52 | Below bar | 0 · 0 · 3 |
| Street Wear | 4/4 | 6/6 | Pass · 14/15 items | −1.65 / 0.52 | Below bar | 0 · 0 · 3 |
| Voltix Bulb | 4/4 | 6/6 | Pass · 15/15 items | +0.33 / 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 stopped before delivering a video1
Off Case
Delivery failures
Every delivered video passes its four delivery tests.
Guard failures
- Repeated footage2
- Faces cut by the frame2
- Dead air1
- One-sided sound1
Reproduce
Run this setup
# DeepSeek Flash · 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 deepseek/deepseek-flash
# after all 56 tasks, one attempt each:
timelinebench aggregate <jobs-dir>Setup id opencode__deepseek-flash__skills-off · model deepseek/deepseek-flash · run guide
Disclosures
- One run per task.
- The reference edits are professional edits, not certified ground truth.