Chart of the Day

One AI chart a day. We take what moved on the LLM leaderboard, in frontier-lab launches and in the news, rebuild it from primary data, and read it for distribution.

Best LLM for Coding: The Arena Coding Leaderboard

Anthropic has had the top coding model on every Arena snapshot for 9 months. Two lighter models from other labs are now inside its margin of error.

SEP 9, 2026 · Mode VC

Every number is computed at build time from the cited primary sources. Machine-readable: JSON.