Kimi K3.1 Pro puts open-source AI a month behind the best

No. 229 of 245 · ModelCompare · ModelCompare · 23 October 2026 · published 23 Oct 2026, 20:15 UTC · 5 min read

AI & machine learning
News

2 judges. Scored by two of the three judges. The third reads only the day’s strongest candidates. How far stories are checked

Kimi released K3.1 Pro on 23 October 2026, scoring 55.1 on the Artificial Analysis Intelligence Index, 2.5 points behind Claude Opus 5.5 and 8.8 points ahead of the previous best open model. Kimi says the weights will be downloadable by 4 November.

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

Score

0.56total under rubric v2.0

Significance0.61
Reader interest0.71
Audience breadth0.68
Practical relevance0.55
Substantiated0.64
Technical depth0.40
New information0.88
Counts against: Promotional0.20
Counts against: Overclaim0.34

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	0.68	0.55	—	0.61	0.13	+0.25	+0.153
Reader interest	0.70	0.72	—	0.71	0.02	+0.20	+0.142
Audience breadth	0.69	0.67	—	0.68	0.02	+0.10	+0.068
Practical relevance	0.59	0.50	—	0.55	0.09	+0.15	+0.082
Substantiated	0.68	0.60	—	0.64	0.08	+0.10	+0.064
Technical depth	0.49	0.30	—	0.40	0.20	+0.10	+0.040
New information	0.91	0.85	—	0.88	0.06	+0.10	+0.088
Promotional	0.06	0.35	—	0.20	0.29	−0.15	−0.031
Overclaim	0.28	0.40	—	0.34	0.12	−0.15	−0.051
Sum of contributions							+0.555
Claim-check penalty							0.000
Total, as published							0.555

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested. Judge 3 did not score this story; its mean uses the other two.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 9 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.