DeepSeek V4 Pro 0813 (max) vs MiniMax M3
Should you write with DeepSeek V4 Pro 0813 (max) or MiniMax M3? 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. DeepSeek V4 Pro 0813 (max) leads overall, 84.8 to 82.7.
The verdict
At about two cents per script each, price won't decide this one, and both are open weights. So it comes down to the scripts themselves. DeepSeek V4 Pro 0813 (max) ranks #56 to MiniMax M3's #71, leads Substance, Accuracy & Value by three and a half points, and is almost five points ahead on YouTube Best Practices. With cost and licensing level, the quality order is the whole decision, and the board separates these two cleanly enough that I'd trust it. MiniMax M3 is better at hitting the target length and quicker to return a script, about two minutes against a bit over three. If you're tight on length, that's a real reason. For most scripts, I'd take DeepSeek's content and handle the length in the edit.
Pick DeepSeek V4 Pro 0813 (max) when you want more substance and structure and don't mind fixing the length.
Pick MiniMax M3 when the script has to land on length and come back quickly.
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 DeepSeek V4 Pro 0813 (max), orange is MiniMax M3, 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, YouTube Best Practices does the most to put DeepSeek V4 Pro 0813 (max) ahead: it leads there by 4.6 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. They cost about the same per script.
| DeepSeek V4 Pro 0813 (max) | MiniMax M3 | |
|---|---|---|
| Overall / 100 | 84.8 | 82.7 |
| Writing Elo | 1917 | 1672 |
| Score spread across drafts (± overall std) | 4.040 | 1.980 |
| Cost per script (USD) | 0.021 | 0.023 |
| Avg time per script (min) | 3.2 | 1.8 |
| Open weights | Yes | 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: DeepSeek V4 Pro 0813 (max) · MiniMax M3. The whole scoring pipeline is on the methodology page.
← All comparisons