evals.report
BenchmarksLabsCompareRun guidesIn the wild

WebArena

A reproducible, self-hostable web environment of fully functional sites (e-commerce, content management, social forum, and software development) where autonomous agents are scored on the functional-correctness success rate of completing 812 realistic, long-horizon, multi-step web tasks.

AgentsTask success rateHigher is better

What this benchmark measures

A reproducible, self-hostable web environment of fully functional sites (e-commerce, content management, social forum, and software development) where autonomous agents are scored on the functional-correctness success rate of completing 812 realistic, long-horizon, multi-step web tasks.

Rows on this page are sourced from public benchmark artifacts, leaderboard exports, or source-linked model reports. Each row keeps benchmark version, source model name, and available run details attached to the score.

The metric shown here is Task success rate. It should be interpreted within WebArena, not compared as part of a site-wide ranking.

No composite ranking
evals.report never combines benchmarks. Task success rate on WebArena is its own number — don’t average it with other metrics.

Frequently asked

What is WebArena?

A reproducible, self-hostable web environment of fully functional sites (e-commerce, content management, social forum, and software development) where autonomous agents are scored on the functional-correctness success rate of completing 812 realistic, long-horizon, multi-step web tasks. It is a agents benchmark measured by Task success rate.

What does Task success rate mean on WebArena?

WebArena reports Task success rate (%); higher is better. Scores are shown only within WebArena and are never averaged with other benchmarks.

What is the top reported WebArena score?

Claude Opus 4.6 has the top reported score on WebArena: 68.0% (Task success rate).

Why do WebArena scores differ across runs?

Harness, scaffold, reasoning effort, and prompt setup change results, so two runs of the same model can differ. evals.report keeps each score with its run context so the differences stay visible.

Does evals.report rank models across benchmarks?

No. WebArena scores are shown within their own metric; evals.report never combines benchmarks into a composite ranking or a single "best model".