MiniMax M3 vs DeepSeek V4 Pro (xhigh)
Should you write with MiniMax M3 or DeepSeek V4 Pro (xhigh)? 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. MiniMax M3 leads overall, 82.7 to 78.9.
The verdict
MiniMax M3 is the better budget writer here. It ranks #71 to DeepSeek V4 Pro (xhigh)'s #97, about 255 Elo ahead, and it wins all nine metrics. The biggest gaps are visual cues and Length Adherence, eleven or twelve points each, so MiniMax scripts come back closer to the right size and with more usable cues. Both are open weights and both are cheap: DeepSeek costs about $0.013 a script against an estimated $0.023 for MiniMax. That's about a penny of difference for a clear step up in quality. DeepSeek V4 Pro (xhigh) is only the better pick if you're standardized on this exact route and every fraction of a cent counts.
Pick MiniMax M3 when you want the better open-weights budget script for about a penny more.
Pick DeepSeek V4 Pro (xhigh) only if you're standardized on this exact DeepSeek route.
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 MiniMax M3, orange is DeepSeek V4 Pro (xhigh), 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, Length Adherence does the most to put MiniMax M3 ahead: it leads there by 11.2 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: MiniMax M3 costs about 1.8x as much per script as DeepSeek V4 Pro (xhigh).
| MiniMax M3 | DeepSeek V4 Pro (xhigh) | |
|---|---|---|
| Overall / 100 | 82.7 | 78.9 |
| Writing Elo | 1672 | 1417 |
| Score spread across drafts (± overall std) | 1.980 | 3.840 |
| Cost per script (USD) | 0.023 | 0.013 |
| Avg time per script (min) | 1.8 | 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: MiniMax M3 · DeepSeek V4 Pro (xhigh). The whole scoring pipeline is on the methodology page.
← All comparisons