Qwen3.8 Max vs GLM-5
Should you write with Qwen3.8 Max or GLM-5? 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. Qwen3.8 Max leads overall, 83.2 to 82.8. GLM-5 still ranks higher on Elo, #66 to #68. Their per-model Elo intervals overlap on this board.
The verdict
The board can't really separate these two on quality, and that's worth knowing before you choose. GLM-5 is #66 and Qwen3.8 Max #68, but Qwen3.8 Max has the slightly higher overall score, and the Elo ranges overlap. Why the mismatch? Elo compares each model's average on every script with every other model's, and a gap smaller than their run-to-run noise counts as a draw, so rank and average can disagree when the margins are this thin. They score well on different things: GLM-5 is closer to my reference voice and scores higher on the hook; Qwen3.8 Max lands the length and writes better cues. Where they do separate is cost and speed. GLM-5 is about three times cheaper, $0.050 per script against $0.161, faster, and open. That tips it for me.
Pick GLM-5 for a closer voice and stronger hook at a much lower price, with open weights.
Pick Qwen3.8 Max when precise length and clean visual cues matter more than cost.
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 Qwen3.8 Max, orange is GLM-5, 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 Qwen3.8 Max ahead: it leads there by 15.5 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: Qwen3.8 Max costs about 3.2x as much per script as GLM-5.
| Qwen3.8 Max | GLM-5 | |
|---|---|---|
| Overall / 100 | 83.2 | 82.8 |
| Writing Elo | 1682 | 1692 |
| Score spread across drafts (± overall std) | 1.980 | 2.400 |
| Cost per script (USD) | 0.161 | 0.050 |
| Avg time per script (min) | 7.2 | 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: Qwen3.8 Max · GLM-5. The whole scoring pipeline is on the methodology page.
← All comparisons