DeepSeek V4 Flash 0731 vs MiniMax M3
Should you write with DeepSeek V4 Flash 0731 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 Flash 0731 leads overall, 84.4 to 82.7.
The verdict
Neither of these is near the top of the board, but if you're shopping at this price, I'd use DeepSeek V4 Flash 0731. It ranks #59 against #71 for MiniMax M3, and its lead is in substance and structure: about three points on Substance, Accuracy & Value and four on YouTube Best Practices, so the judges found more to learn and more of the YouTube beats in its scripts. MiniMax M3 does hit the target length better, its visual cues are a hair ahead, and it's a bit faster. But DeepSeek costs $0.005 per script against about $0.023, and both are open weights, so the cheaper one is also the one with more to say. Choose MiniMax M3 when length and turnaround matter more to you than depth.
Pick DeepSeek V4 Flash 0731 for more substance and better YouTube structure at the lower price.
Pick MiniMax M3 when you need scripts that hit the target length and come back a little faster.
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 Flash 0731, 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 Flash 0731 ahead: it leads there by 3.9 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. DeepSeek V4 Flash 0731 is ahead and it's also the cheaper one: MiniMax M3 costs about 4.6x as much per script.
| DeepSeek V4 Flash 0731 | MiniMax M3 | |
|---|---|---|
| Overall / 100 | 84.4 | 82.7 |
| Writing Elo | 1866 | 1672 |
| Score spread across drafts (± overall std) | 3.360 | 1.980 |
| Cost per script (USD) | 0.005 | 0.023 |
| Avg time per script (min) | 3.1 | 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 Flash 0731 · MiniMax M3. The whole scoring pipeline is on the methodology page.
← All comparisons