Gemini 3.1 Pro Preview
Google · OpenCode 1.18.31 · guidance off
Rank 16 of 16Verified · run and scored by the TimelineBench teamOpenCode 1.18.31guidance off
Resolution rate
1.8%[0.0, 9.6] exact 95% CI
1 of 56 tasks resolved, one attempt each
- Tests passed
- 19/56
- delivery + guards + must-haves
- Must-haves passed
- 32/56
- 57.1% [43.2, 70.3]
- Editors' win-or-tie
- 9.0%
- [3.9, 14.0] · 161 votes
- Rank · bootstrap interval
- 16 · 14.5–16
- by resolution rate, of 16 setups
- Videos delivered
- 54/56
- 2 missing
- Median runtime
- 15.9 min
- 16.5 h in total
- Auto Elo
- 182
- [182, 376] · pro cut 1000
- Editor Elo
- 541
- [399, 623]
- Cost
- Not recorded
- recorded for Claude Code only
- 01 / 04
Delivery tests
54 videos delivered; the four tests of each task's tests/test.sh.
50pass · 89.3% - 02 / 04
Content guards
Silent, frozen, looped, dead air, one-sided sound, faces cut.
33still standing · 58.9% - 03 / 04
Brief must-haves
Every validated must-have of the brief.
19pass all tests · 33.9% - 04 / 04
Quality bar
Panel gap against the professional cut reaches the collection's tie margin.
1resolved · 1.8%
By collection
EditStock0/11resolved · 5/11 pass tests · bar 0.21
Cinestudy1/15resolved · 5/15 pass tests · bar 0.30
UGC0/15resolved · 6/15 pass tests · bar 1.54
Commercial0/15resolved · 3/15 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 | Fail · 8/15 items | −3.40 / 0.21 | Failed a test | 0 · 0 · 3 |
| BOS Parkour | 4/4 | 6/6 | Pass · 9/9 items | −2.15 / 0.21 | Below bar | 0 · 0 · 3 |
| Evolve By Training Camp | 4/4 | 6/6 | Pass · 9/9 items | −3.11 / 0.21 | Below bar | 0 · 0 · 3 |
| Incubate | 4/4 | Mostly frozen | Fail · 4/15 items | −4.42 / 0.21 | Failed a test | 0 · 0 · 3 |
| J-Pops | 3/4 · video | Mostly frozen | Pass · 8/15 items | −4.23 / 0.21 | Failed a test | 0 · 0 · 3 |
| Klug Fitness Brand Story | 4/4 | 6/6 | Pass · 13/15 items | −1.21 / 0.21 | Below bar | 0 · 0 · 3 |
| Klug Fitness Next Time | 4/4 | 6/6 | Pass · 14/15 items | −1.27 / 0.21 | Below bar | 1 · 0 · 2 |
| Klug Fitness Railroad Track | 4/4 | Mostly frozen | Fail · 9/15 items | −3.73 / 0.21 | Failed a test | 0 · 0 · 3 |
| Two Player | 4/4 | 6/6 | Fail · 4/15 items | −2.68 / 0.21 | Failed a test | 0 · 0 · 3 |
| Whisper Fan | 4/4 | 6/6 | Pass · 6/7 items | −2.40 / 0.21 | Below bar | 1 · 0 · 2 |
| Wild Planet | 4/4 | One-sided sound | Pass · 6/8 items | −2.36 / 0.21 | Failed a test | 0 · 0 · 3 |
| Cinestudy · 1/15 resolved · tie margin 0.30 | ||||||
| Car Chase | 4/4 | Faces cut by the frame | Pass · 9/13 items | −1.08 / 0.30 | Failed a test | 0 · 0 · 3 |
| Color Grading | No output · output-token limit | — | — | — | No output | — |
| Compression Of Time | 4/4 | 6/6 | Pass · 15/15 items | −2.15 / 0.30 | Below bar | 0 · 0 · 3 |
| Cutting On Motion | 4/4 | Mostly silent | Pass · 8/14 items | −2.45 / 0.30 | Failed a test | 0 · 0 · 3 |
| Documentary Format | 4/4 | 6/6 | Pass · 10/15 items | −1.51 / 0.30 | Below bar | 0 · 0 · 3 |
| Editing A Sequence | 4/4 | 6/6 | Fail · 12/15 items | +0.10 / 0.30 | Failed a test | 1 · 0 · 2 |
| Horror Movie | 4/4 | Mostly silent, Dead air | Fail · 12/15 items | −1.14 / 0.30 | Failed a test | 0 · 0 · 3 |
| Hospital Scene | 4/4 | 6/6 | Fail · 8/15 items | −1.28 / 0.30 | Failed a test | 0 · 0 · 3 |
| License Exam | No output · stopped early | — | — | — | No output | — |
| Movie Trailer | 4/4 | 6/6 | Pass · 12/15 items | +0.37 / 0.30 | Resolved | 0 · 0 · 3 |
| Podcast Documentary | 4/4 | 6/6 | Pass · 12/15 items | −2.04 / 0.30 | Below bar | 0 · 1 · 2 |
| Refractory | 4/4 | Dead air | Pass · 12/15 items | −1.91 / 0.30 | Failed a test | 0 · 0 · 3 |
| Relationship Card | 4/4 | Dead air | Pass · 12/15 items | −1.92 / 0.30 | Failed a test | 0 · 0 · 3 |
| Restaurant Scene | 4/4 | 6/6 | Pass · 9/15 items | −2.83 / 0.30 | Below bar | 0 · 0 · 3 |
| The Intern Mockumentary | 4/4 | Dead air | Pass · 12/14 items | −1.55 / 0.30 | Failed a test | 0 · 0 · 3 |
| UGC · 0/15 resolved · tie margin 1.54 | ||||||
| Breathex Nose Patches | 4/4 | 6/6 | Fail · 9/15 items | −2.86 / 1.54 | Failed a test | 0 · 0 · 3 |
| CUPNEX | 4/4 | 6/6 | Fail · 12/15 items | +0.01 / 1.54 | Failed a test | 1 · 0 · 2 |
| Dazzle and Charm | 4/4 | 6/6 | Fail · 12/15 items | +1.12 / 1.54 | Failed a test | 0 · 2 · 1 |
| Feel Comfy | 3/4 · duration | 6/6 | Pass · 11/14 items | −2.48 / 1.54 | Failed a test | 0 · 0 · 3 |
| Fitness Venue | 4/4 | 6/6 | Pass · 13/15 items | +0.31 / 1.54 | Below bar | 0 · 0 · 3 |
| Global Physiotherapy Clinic | 4/4 | 6/6 | Fail · 6/15 items | −1.01 / 1.54 | Failed a test | 0 · 0 · 3 |
| House of Hue | 4/4 | 6/6 | Pass · 11/15 items | −0.83 / 1.54 | Below bar | 0 · 0 · 3 |
| LeadLoop | 4/4 | 6/6 | Fail · 8/15 items | −0.96 / 1.54 | Failed a test | 0 · 0 · 3 |
| LedgeFin | 4/4 | 6/6 | Pass · 13/15 items | −0.39 / 1.54 | Below bar | 0 · 0 · 3 |
| MotionMix Studio | 4/4 | 6/6 | Pass · 13/15 items | −1.41 / 1.54 | Below bar | 0 · 0 · 3 |
| Nova Sole | 4/4 | 6/6 | Fail · 10/15 items | −1.24 / 1.54 | Failed a test | 0 · 0 · 3 |
| Off Case | 4/4 | 6/6 | Fail · 6/15 items | −3.09 / 1.54 | Failed a test | 0 · 0 · 3 |
| Personal Branding | 4/4 | 6/6 | Pass · 11/15 items | −0.39 / 1.54 | Below bar | 0 · 0 · 3 |
| Personal Introduction | 4/4 | Mostly frozen | Fail · 13/15 items | −0.37 / 1.54 | Failed a test | 0 · 0 · 3 |
| Portable Side Bag | 4/4 | 6/6 | Pass · 10/15 items | −0.16 / 1.54 | Below bar | 0 · 0 · 3 |
| Commercial · 0/15 resolved · tie margin 0.52 | ||||||
| Aroma Candle | 4/4 | Mostly frozen | Fail · 3/15 items | −3.99 / 0.52 | Failed a test | 0 · 0 · 3 |
| Bean & Roast | 4/4 | Dead air | Fail · 12/15 items | −0.31 / 0.52 | Failed a test | 0 · 1 · 2 |
| Beauty of Delhi | 4/4 | 6/6 | Pass · 8/15 items | −1.06 / 0.52 | Below bar | 0 · 1 · 2 |
| Bike Ride | 3/4 · audio | 6/6 | Fail · 9/15 items | −0.68 / 0.52 | Failed a test | 0 · 0 · 3 |
| Camera | 4/4 | Mostly silent | Pass · 9/15 items | −2.38 / 0.52 | Failed a test | 1 · 0 · 2 |
| Fortunex | 4/4 | 6/6 | Pass · 10/15 items | −1.18 / 0.52 | Below bar | 1 · 0 · 2 |
| Hard Life Of Athlete | 3/4 · audio | 6/6 | Pass · 11/15 items | −0.42 / 0.52 | Failed a test | 1 · 0 · 2 |
| Loom Craft | 4/4 | Mostly frozen | Fail · 6/15 items | −3.54 / 0.52 | Failed a test | 0 · 0 · 3 |
| Motionmix In Charge | 4/4 | Mostly frozen | Pass · 8/13 items | −1.82 / 0.52 | Failed a test | 0 · 1 · 2 |
| Pro Bite | 4/4 | 6/6 | Fail · 3/15 items | −3.21 / 0.52 | Failed a test | 0 · 0 · 3 |
| Quickshine | 4/4 | 6/6 | Fail · 4/14 items | −1.75 / 0.52 | Failed a test | 0 · 1 · 1 |
| Shadow Airpod | 4/4 | Mostly silent, Dead air | Pass · 14/15 items | −1.67 / 0.52 | Failed a test | 0 · 0 · 3 |
| Standcup | 4/4 | 6/6 | Pass · 7/15 items | −1.52 / 0.52 | Below bar | 0 · 0 · 3 |
| Street Wear | 4/4 | One-sided sound | Pass · 10/15 items | −1.42 / 0.52 | Failed a test | 0 · 0 · 3 |
| Voltix Bulb | 4/4 | 6/6 | Fail · 12/15 items | −0.94 / 0.52 | Failed a test | 0 · 0 · 3 |
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
- Degenerate output hit the output-token limit1
License Exam, Color Grading
Delivery failures
- audio2
- video1
- duration1
Guard failures
- Mostly frozen7
- Dead air6
- Mostly silent4
- One-sided sound2
- Faces cut by the frame1
Reproduce
Run this setup
# Gemini 3.1 Pro Preview · 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 google/gemini-3.1-pro-preview
# after all 56 tasks, one attempt each:
timelinebench aggregate <jobs-dir>Setup id opencode__gemini-3.1-pro-preview__skills-off · model google/gemini-3.1-pro-preview · run guide
Disclosures
- One run per task.
- The reference edits are professional edits, not certified ground truth.