How Each Model Behaves

Real-world behavioral analysis and performance benchmarking of frontier AI models

Description

A comprehensive data visualization dashboard derived from a ClickHouse database of thousands of model requests. It benchmarks specific behaviors across Claude and Codex versions, including output tokens per second, git command patterns, shell command complexity, and tool-calling efficiency.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: Provides unique, data-driven insights into the distinct 'personalities' and coding habits of different frontier models…
Attributed to: @theo
Built with: Codex
Tags: #benchmarking #analytics #clickhouse #developer-tools

Discovered: X
First posted: X · Oct 14, 2026
Listed: Added 1h ago
Build: Strong
Models: Strong