all the models — AI benchmark observatory
← Benchmarks

Web Bench

Web Bench evaluates agents on realistic web-development engineering tasks, measuring end-to-end implementation in browser-based workflows.

id web-bench · max 1 · 2 models reported

#ModelScore
1Seed 2.1 Pro
ByteDance
0.78
2Seed 2.1 Turbo
ByteDance
0.74
Web Bench Leaderboard · all the models