Benchmark Almanac

AfterQuery

We track 2 benchmarks and 2 arenas that AfterQuery made or helped make.

0 in use 1 with public code 2 with a leaderboard here

Arena leaderboards

Top five in each of its 1 arena with three or more rated models, the most rated first. We don't have a leaderboard yet for one other, listed below.

Benchmarks

Name Kind Released Best score Status
StoreBench Agents manage a simulated apparel store in Medusa. They order inventory, change prices, ship purchases, and process refunds as demand changes. Running a business Oct 2026 0.83 Not in cards
App-Bench Coding agents build six full-stack web applications from a single prompt. Two developers grade implemented features against 151 rubric items. The score uses each tool’s best result from three attempts per application. Building whole projects Dec 2025 67.5% Not in cards

Arenas without a leaderboard here

Name Kind Released Best score Status
UI-Bench AI website builders generate sites from 30 text prompts. Experts compare paired sites without seeing the builder names. A TrueSkill-derived model converts preferences into ratings with confidence intervals. Web and app front ends Aug 2025 Not in cards