MiniMaxAI/MiniMax-M3.1-Flash

No. 133 of 245 · huggingface.co · published 23 Oct 2026, 01:09 UTC · 3 min read

Programming & dev tools
AI & machine learning
Release

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

MiniMax has released MiniMax-M3.1-Flash on Hugging Face, a native multimodal mixture-of-experts model (about 428B total parameters, 23B active per token) with text, image, and video inputs and a context window of up to 1M tokens.

Read the original at huggingface.co. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.65total under rubric v2.0Contestedjudges differ by 0.44 on substantiated

Significance0.71
Reader interest0.76
Audience breadth0.64
Practical relevance0.80
Substantiated0.69
Technical depth0.70
New information0.93
Counts against: Promotional0.23
Counts against: Overclaim0.44

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.71	0.60	0.82	0.71	0.22	+0.25	+0.177
Reader interest	0.68	0.70	0.90	0.76	0.22	+0.20	+0.152
Audience breadth	0.55	0.60	0.78	0.64	0.23	+0.10	+0.064
Practical relevance	0.86	0.70	0.85	0.80	0.16	+0.15	+0.120
Substantiated	0.89	0.45	0.72	0.69	0.44 , above the contested threshold	+0.10	+0.069
Technical depth	0.74	0.60	0.76	0.70	0.16	+0.10	+0.070
New information	0.90	0.90	1.00	0.93	0.10	+0.10	+0.093
Promotional	0.10	0.30	0.28	0.23	0.20	−0.15	−0.034
Overclaim	0.43	0.50	0.38	0.44	0.12	−0.15	−0.066
Sum of contributions							+0.647
Claim-check penalty							0.000
Total, as published							0.647

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

vLLM Delivers Day-0 Support for MiniMax-M3.1-Flash · vLLM Blog
M3.1 Flash weights are now open · together.ai

Elsewhere

Elsewhere: HN 2 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.