Lab notes

News, methodology and analysis

What changed in each cycle, how the measurements are taken, and the limits of what a composite index can tell you.
All lab notes
DateCategoryTitleSummaryRead
19 Aug 2026methodologyThis cycle's composite recompute, and why it barely moved most rowsWe re derived every composite index from the ten published axis weights and the stored subscores, row by row, and checked the arithmetic against the methodology page. Here is what changed and what that process actually verifies.2 min
18 Aug 2026newsWindsurf is gone from the indexwindsurf.com now redirects to devin.ai/desktop. The product is discontinued, so it has been removed from the roster, the raw runs, every leaderboard, every compare pair and the matrix, not just flagged as inactive.2 min
15 Aug 2026newsAugust 2026 index update: three products move, one regressionThe fourth full run of the vibeOps specification against 11 products. Two products improved their reliability materially, one regressed on tenancy isolation.1 min
14 Aug 2026methodologyWhy we publish the spread and not the meanA single average build time hides the thing you actually care about: how bad the slow runs get. Here is the p10 to p90 data for every product in the index.2 min
12 Aug 2026analysisServer rendering is the whole GEO story right nowWe disabled JavaScript on every generated marketing page and counted the bytes of real text. The gap between the top and the bottom of the cohort is nearly seven to one.1 min
09 Aug 2026methodologyHow we score agent performance without reading the chat logAgent performance is 18 points of the index, the joint largest weight. Here is exactly how a prompt earns 0, 50 or 100.1 min
07 Aug 2026methodologyReproducing any row in the index by handThe composite is a weighted sum, nothing more. Take the ten subscores off any product page, multiply by the published weights and you get the number in the table.1 min
03 Aug 2026analysisWhat this benchmark cannot tell youA composite index is a compression of a complicated thing into one number. Here are the limits of ours, stated plainly.1 min

methodology

4 published

news

2 published

analysis

2 published