| Characteristic | Score* |
|---|---|
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
| - | - |
The chart is not accessible to screen readers. Please switch to the table view to access the data.
Download
Source
Source
Release date
January 2026
More information
Region
Worldwide
Survey time period
January 2026
Supplementary notes
* The is an open platform for evaluating AI chatbots, where the public community participates in AI benchmarking by voting. Two anonymous AI chatbots are questioned until the user decides which one provides the better answers.
Each vote is used to update the models’ Arena scores, which are based on an Elo rating system. The score reflects how often a model wins head-to-head comparisons against other models, weighted by the strength of its opponents. Higher scores thus indicate stronger overall performance relative to other models in the Arena, rather than an absolute measure of quality.
Citation formats
