Watch the progress of frontier models in bringing Ancient Rome to life on Arena, from Q4 2025 to now.
Scores for Claude Sonnet 5.5 by AnthropicAI and GPT-6.1 by OpenAI are coming soon. Real-world tasks from our global community of users power the Arena leaderboards. Head to
A quick explanation of the new model “Sonnet 5.5” in 3 minutes
Differences between Sonnet 5 and Sonnet 5.5 We have summarized how to properly use higher-end models such as Opus 5.5 and Fable 5.1. A quick summary is as follows. ・From Sonnet 5, the number of practical tasks for command operations has been increased by approximately 7 times. Price remains unchanged ・Top Opus…
I didn't expect the cheaper Claude to get this close to Opus
Claude Sonnet 5.5 is out. on a coding test built from real Cursor sessions, its best score sits about two points behind Opus 5.5, with input and output tokens priced at half Opus's rates the bill: $2 / 1M input
Spent ~3 hours building a Rube Goldberg machine in Blender
Without touching a single vertex myself.Cursor + Opus 5.5 → Blender MCP → Blender13 stages: gears, Newton's cradle, bucket wheel, Geneva drive, cam bell, Archimedes screw… and it loops. 🤯: we started at 5:14 PM, and
You have reached the end of the archive
All of Claude Opus 5