Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Agentic benchmark
WebArena-Verified Browser Agent Benchmark. Every model the catalog carries a published WebArena-Verified value for, ranked by that value.
WebArena-Verified is an audited release of the WebArena browser-agent benchmark. It rechecks task descriptions, reference answers, and evaluators, and replaces nondeterministic judging with deterministic checks where possible. 5 models in the ModelChoice catalog have a published value.
Each point is a model with a published WebArena-Verified value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
5 models with a published WebArena-Verified value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Deterministic end-state task success |
|---|---|---|---|
| 1 | Meta | 69 | |
| 2 | Alibaba | 66.8 | |
| 3 | Alibaba | 64.8 |
What the benchmark measures and how its value is published, from the source’s own record.
WebArena-Verified (WebArena-Verified Browser Agent Benchmark) is an agentic benchmark published by WebArena-Verified: A Fully Audited Benchmark for Web Agents. WebArena-Verified is an audited release of the WebArena browser-agent benchmark. It rechecks task descriptions, reference answers, and evaluators, and replaces nondeterministic judging with deterministic checks where possible. Its evaluation set is described by the source as 812 verified tasks; separate 258-task Hard subset. The source rates its difficulty as audited stateful browser work.
Each model's result is published by WebArena-Verified: A Fully Audited Benchmark for Web Agents as deterministic end-state task success. ModelChoice prints that value exactly as published, and never converts or rescales it. This page ranks the 5 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | LiquidAI | 38.42 |
| 5 | LiquidAI | 26.75 |
Evidence key: Observed
Rows are ordered by the value WebArena-Verified: A Fully Audited Benchmark for Web Agents published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.