https://blog.scrymore.com Benchmarks and cost/performance results for vision-language models and agents doing mobile UI and Figma-to-Storybook diff review. en-us Mon, 19 Oct 2026 01:23:44 GMT https://blog.scrymore.com/blog/dark-factory-tiers/ https://blog.scrymore.com/blog/dark-factory-tiers/ Mon, 19 Oct 2026 12:00:00 GMT We graded 134 shipped features and fixes by the weakest model set that could finish them in an autonomous run. Six fit a Haiku-only build. 87 run longer than any measured model can finish reliably in one attempt, and 12 are beyond one autonomous run today. agents dark-factory metr model-comparison ai-coding https://blog.scrymore.com/blog/dark-factory-patterns/ https://blog.scrymore.com/blog/dark-factory-patterns/ Mon, 19 Oct 2026 12:00:00 GMT A field guide to shipping software with the lights off: 25 patterns in five families, from one human message to a retro that has to pass a check. Each pattern comes with our own run evidence and published work by others. agents dark-factory ci release-engineering ai-coding https://blog.scrymore.com/blog/prodia-speed-flux3-own-gpus/ https://blog.scrymore.com/blog/prodia-speed-flux3-own-gpus/ Sat, 17 Oct 2026 12:00:00 GMT We built a Google Images where every picture is generated, ran it on hosted Prodia and on self-hosted FLUX.3 klein, and measured how close our own RTX 5090s got. On 8 RTX 5090s with 384 px tiles we are ahead on the full screen and close on the first picture. image-generation flux latency gpu prodia https://blog.scrymore.com/blog/cheaper-design-diffs-cascade/ https://blog.scrymore.com/blog/cheaper-design-diffs-cascade/ Fri, 25 Sep 2026 12:00:00 GMT On 60 Figma-to-Storybook screens with judged truth, a deterministic pre-filter plus one cheap vision call matches Claude Opus 5.5 xhigh's recall of human-tagged defects for $0.0045 a screen instead of $0.54. Scry's Basic and Plus tiers, built on it, find 89% and 94% for $0.009 and $0.05. figma storybook agents model-comparison benchmark leaderboard evaluation cost https://blog.scrymore.com/blog/link-figma-to-any-storybook/ https://blog.scrymore.com/blog/link-figma-to-any-storybook/ Fri, 25 Sep 2026 12:00:00 GMT Scry Link connects Figma layers to stories in any hosted Storybook, auto-matches a whole page, and shows where the design and the implementation have drifted apart. figma storybook design-systems handoff plugin https://blog.scrymore.com/blog/component-requests-figma-to-github-issue/ https://blog.scrymore.com/blog/component-requests-figma-to-github-issue/ Fri, 25 Sep 2026 12:00:00 GMT Select a component in Figma that has no code yet, press Request this component, and Scry opens a GitHub issue with a preview, the variants and your notes. The Figma node remembers it. figma storybook design-systems github scry-link product https://blog.scrymore.com/blog/cheaper-diff-agents-five-more-models/ https://blog.scrymore.com/blog/cheaper-diff-agents-five-more-models/ Fri, 28 Aug 2026 12:00:00 GMT Sixteen model configurations on the same Figma-to-Storybook diff. The cheapest run that still finds the structural problems now costs under a cent. figma storybook agents model-comparison cost benchmark https://blog.scrymore.com/blog/beyond-screenshots-figma-storybook-diff-agents/ https://blog.scrymore.com/blog/beyond-screenshots-figma-storybook-diff-agents/ Mon, 20 Jul 2026 12:00:00 GMT What changes when a UI review agent gets the Figma layer tree, the live DOM with computed styles and the implementation source instead of just two screenshots. figma storybook agents ui-review design-systems https://blog.scrymore.com/blog/introducing-scry-design-diff-eval/ https://blog.scrymore.com/blog/introducing-scry-design-diff-eval/ Fri, 03 Jul 2026 12:00:00 GMT Scry Design Diff Eval is a 311-pair benchmark of human-reviewed mobile UI defects. The best vision-language models recover roughly two fifths of known issues. benchmark vision-language-models mobile-ui visual-regression evaluation