# Artificial Analysis finds GPT-6 Astra more consistent than Kimi K3.1 Pro on VIALS

> Original title: Solving a task once does not mean a model will answer it consistently, and consistency is a key part of the advantage for frontier models...

- Source: Artificial Analysis
- Published: 2026-11-06T17:09:38.000Z
- Bad Influence: https://badinfluence.news/items/bjvnqwf7o0pqq6iq4ufl8lkm2
- Original: https://x.com/ArtificialAnlys/status/2118752683783811153

## Summary

Artificial Analysis reports that Kimi K3.1 Pro solves 119 of 161 VIALS tasks at least once across three attempts, versus 118 for GPT-6 Astra. Requiring all three attempts to succeed, Kimi passes 73 tasks (45%) and Astra passes 101 (63%).

## Post

Solving a task once does not mean a model will answer it consistently, and consistency is a key part of the advantage for frontier models on VIALS

Kimi K3.1 Pro answers 119 of 161 tasks correctly at least once across three attempts, compared with 118 of 161 tasks for GPT-6 Astra. Requiring all three attempts to succeed changes the picture: Kimi passes 73 tasks (45%), while Astra passes 101 (63%)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWdSVmDWAAAtCGL.jpg&mode=thumb&exp=1794182400&sig=e0795e7d6b8aee64)