Scale AI NYC Meetup: Advancements in Benchmarking Coding Agents

jyangballin · x · 2026-07-30

Scale AI announced its third Research Meetup in NYC, diving deep into benchmarking for coding agents. The event features talks from researchers at Meta, Columbia University, and Scale AI, presenting updates on various benchmarks including ProgramBench, BranchBench, Terminal Bench, and SWE Atlas.

Original post →

More from coding & agent

coding & agent channel →