Grok 4.6 (high) vs DeepSeek V4 Flash 0731
Should you write with Grok 4.6 (high) or DeepSeek V4 Flash 0731? On this page the only thing that changes is the model. Both wrote their own version of the scripts behind 10 of my What's AI videos, five drafts per script, and three judges from three model families scored every draft blind, with my finished script as the reference. Grok 4.6 (high) leads overall, 85.9 to 84.4. Their per-model Elo intervals overlap on this board.
The verdict
Forty times the price for a somewhat better script: that's the trade here. Grok 4.6 (high) ranks #53 against #59, a lead the overlapping Elo ranges leave unproven. Grok wins seven of the nine metrics, most visibly visual cues and continuity, four to six points each. Its weak spot is Hook Strength, almost nine points behind DeepSeek V4 Flash 0731. And the bill is $0.211 per script against half a cent, with open weights on the DeepSeek side. For quality, Grok. For bulk drafting, DeepSeek is the obvious choice.
Pick Grok 4.6 (high) for stronger visual cues, continuity and voice, if you'll fix the hook yourself.
Pick DeepSeek V4 Flash 0731 for a better opening, open weights, and near-free drafts.
How to read these numbers
Overall vs Elo. Overall is the weighted rubric score. Elo compares each model's five-draft average with every other model's, script by script, and counts gaps inside run-to-run noise as draws, so it rewards winning often and can disagree with overall. My own scripts score 90.9 on the same rubric, not a literal 100. Right now 2 of 167 ranked configurations reach it. A model above that line writes at that level on this rubric. That's not the same as beating my script line for line.
Reading the Elo intervals. Each 95% range comes from resampling every model's recorded run scores on each task and re-ranking. Comparing these separate ranges does not test the Elo gap between two models: far apart is strong evidence, and overlap isn't a tie. The tasks stay fixed, so the ranges say nothing about new tasks (the long version).
Metric by metric: where the gap comes from
Blue is Grok 4.6 (high), orange is DeepSeek V4 Flash 0731, and the solid bar takes the metric. The weight under each name is how much it counts toward the overall. Weighted by how much each metric counts, Tone & Voice Match does the most to put Grok 4.6 (high) ahead: it leads there by 3.4 points. If you care about one thing, say voice or length, go straight to that row.
Cost, speed, and consistency
Quality is half the decision. The other half is what each script costs you, how long you wait, and how often you get a bad draft. The lead has a price: Grok 4.6 (high) costs about 42x as much per script as DeepSeek V4 Flash 0731.
| Grok 4.6 (high) | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Overall / 100 | 85.9 | 84.4 |
| Writing Elo | 1970 | 1866 |
| Score spread across drafts (± overall std) | 2.980 | 3.360 |
| Cost per script (USD) | 0.211 | 0.005 |
| Avg time per script (min) | 3.6 | 3.1 |
| Open weights | No | Yes |
Green wins the row, and for spread, cost and time, lower wins. Cost is one script at recorded list prices, uncached and without judging, so your real bill will differ. Spread is how much the overall score moves across a model's drafts, and time is the average time to get one accepted script, retries included.
Want the script-by-script detail? Full scorecards: Grok 4.6 (high) · DeepSeek V4 Flash 0731. The whole scoring pipeline is on the methodology page.
← All comparisons