Artificial Analysis Finds Kimi K3.1 Pro’s Largest Personality Shift vs. Its Predecessor

1 reports 1 reporting sources Updated 5 hours ago

Understand the event

AI overview

Artificial Analysis reports that Kimi K3.1 Pro had the largest personality shift it has measured between a model and its direct predecessor on AA-PersonalityBench. Across 30 traits, its percentile ranks moved by an average of 30 points from Kimi K3; 18 traits shifted by at least 25 points. Artificial Analysis says the next-largest average shift was 23 points, between GPT-6 Sol and GPT-6.1 Sol. The benchmark ranks each model from 1 to 100 on each trait.

Generated by AI from reports · Updated 3 hours ago

Latest development11/3 06:38 (UTC+8)

In AA-PersonalityBench, Kimi K3.1 Pro shows the biggest personality change we’ve seen compared to a direct predecessor Each model is percentile ranked from 1 to 100 on each of 30 personality traits. Across all 30 traits, Kimi K3.1 Pro's ranks moved by an average of 30 points from Kimi K3's (next largest is 23, for GPT-6 Sol to GPT-6.1 Sol), and 18 of the 30 traits moved by 25 points or more.Artificial Analysis · X

Models in this story

Kimi K3.1 Pro#2 overall$2 input / $10 output per million tokens
Kimi K3#23 overall$0.19 input / $15 output per million tokens
GPT-6 Sol#14 overall$2 input / $10 output per million tokens
GPT-6.1 Sol#8 overall$2 input / $10 output per million tokens

Compare their API prices API prices of all models

Report timeline

Follow the reports to explore different sides of the event.

11/3

06:38
Artificial Analysis · X
In AA-PersonalityBench, Kimi K3.1 Pro shows the biggest personality change we’ve seen compared to a direct predecessor Each model is percentile ranked from 1 to 100 on each of 30 personality traits. Across all 30 traits, Kimi K3.1 Pro's ranks moved by an average of 30 points from Kimi K3's (next largest is 23, for GPT-6 Sol to GPT-6.1 Sol), and 18 of the 30 traits moved by 25 points or more.
In AA-PersonalityBench, Kimi K3.1 Pro shows the biggest personality change we’ve seen compared to a direct predecessor Each model is percentile ranked from 1 to 100 on each of 30 personality traits. Across all 30 traits, Kimi K3.1 Pro's ranks moved by an average of 30 points from Kimi K3's (next largest is 23, for GPT-6 Sol to GPT-6.1 Sol), and 18 of the 30 traits moved by 25 points or more.

Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue

Event heat trend

Current within comparable coverage: 9
Peak within comparable coverage: 911/3 09:00 (UTC+8)
24-hour change: –

Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.