Every MiniMax model, side by side

Skip the MiniMax M2 models for scripts. MiniMax M3 is at #82, and both older rows are far below it, 670 Elo from the top of the family to the bottom. All 3 configurations are open weights and cheap, so money barely enters into it here. What matters is which generation you run.

All 3 configurations

Every configuration here wrote the same 10 scripts for the same four blind judges, so the writing Elo and ranks compare across the whole board, not just inside this family. A highlighted row is a model's best configuration, and the rows under it are the same model at other effort or thinking settings. Scores run 0 to 100, and cost is one full script at the API list price of the route we ran.

Board rank	Configuration	Elo	Overall	Tone	Craft	Substance	Hook	YouTube	Flow	Slop	Length	Cues	Cost / script	Time / script
#82	MiniMax M3 · open	1644 ±33	82.9	82.4	84.6	81.6	84.5	79.8	80.2	85.7	89.7	82.3	$0.023	1.8 min
#144	MiniMax M2 · open	1016 ±47	73.6	74.3	78.1	75.9	80.5	65.3	72.4	82.0	64.3	66.9	$0.0063	0.5 min
#146	MiniMax M2.1 · open	974 ±48	72.5	73.9	77.2	75.7	78.3	61.6	71.7	81.4	65.6	63.3	$0.0063	0.5 min

Which one should you use?

Use MiniMax M3. It's the best writer and the value pick, at $0.023 per script, and it finishes one in 1.8 minutes. Most of its lead over the MiniMax M2 models comes from what makes a draft usable: it lands much closer to the target length, writes better visual cues and follows YouTube best practices more closely. MiniMax M2 costs $0.0063, so yes, it's cheaper, but you give up 628 Elo to save pennies per script. Bad trade.

Also, MiniMax M2.1 didn't improve on MiniMax M2 for writing. The two are within noise of each other. If you're still on either MiniMax M2 model for scripts, upgrading is the easy win.

Every row links to its full scorecard, and the cross-lab match-ups live in the head-to-head comparisons.

← All comparisons