MiniMax M3 vs GLM-5
Should you write with MiniMax M3 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. GLM-5 leads overall, 82.8 to 82.7. Their per-model Elo intervals overlap on this board.
The verdict
I lean GLM-5 here, but only slightly, because on quality the board can't split these two. The overall scores are about 0.1 apart, the ranks are #66 and #71, and the Elo ranges overlap, so the order could easily swap. What differs is where each one scores. GLM-5 is ahead on substance and on YouTube structure, about three points on YouTube Best Practices. MiniMax M3 is far better on length, around eleven points, and writes better visual cues. It's also about half the price, $0.023 per script against $0.050, and quicker. Both are open. If getting the length right and the lower bill matter most to you, MiniMax M3 is the saner pick.
Pick GLM-5 when you want a bit more substance and YouTube structure in the script.
Pick MiniMax M3 when length, visual cues, speed and price matter more than depth.
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 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, YouTube Best Practices does the most to put GLM-5 ahead: it leads there by 3.3 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: GLM-5 costs about 2.2x as much per script as MiniMax M3.
| MiniMax M3 | GLM-5 | |
|---|---|---|
| Overall / 100 | 82.7 | 82.8 |
| Writing Elo | 1672 | 1692 |
| Score spread across drafts (± overall std) | 1.980 | 2.400 |
| Cost per script (USD) | 0.023 | 0.050 |
| Avg time per script (min) | 1.8 | 3.1 |
| 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 · GLM-5. The whole scoring pipeline is on the methodology page.
← All comparisons