DeepSeek V4 Pro 0813 (max) vs Qwen3.8 Max
Should you write with DeepSeek V4 Pro 0813 (max) or Qwen3.8 Max? 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 83.2.
The verdict
Qwen3.8 Max costs almost eight times more per script and still loses. DeepSeek V4 Pro 0813 (max) ranks #56 against #68, and its lead is on the metrics that score whether a script sounds human: close to five points on Tone & Voice Match, plus clear edges on the hook and on continuity. To be fair, Qwen3.8 Max is the tidier writer. It lands the length better, uses fewer slop patterns and writes better visual cues. But tidy with less voice is a weak combination for a script people are supposed to watch. At $0.021 against $0.161, with open weights and faster turnaround, DeepSeek is my pick.
Pick DeepSeek V4 Pro 0813 (max) for a stronger voice and hook at a fraction of the cost, with open weights.
Pick Qwen3.8 Max when tidy prose, clean visual cues and exact length matter more than voice.
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 Qwen3.8 Max, 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 DeepSeek V4 Pro 0813 (max) ahead: it leads there by 4.7 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 Pro 0813 (max) is ahead and it's also the cheaper one: Qwen3.8 Max costs about 7.7x as much per script.
| DeepSeek V4 Pro 0813 (max) | Qwen3.8 Max | |
|---|---|---|
| Overall / 100 | 84.8 | 83.2 |
| Writing Elo | 1917 | 1682 |
| Score spread across drafts (± overall std) | 4.040 | 1.980 |
| Cost per script (USD) | 0.021 | 0.161 |
| Avg time per script (min) | 3.2 | 7.2 |
| Open weights | Yes | No |
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) · Qwen3.8 Max. The whole scoring pipeline is on the methodology page.
← All comparisons