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 Web Agent Benchmark. Every model the catalog carries a published WebArena value for, ranked by that value.
WebArena tests whether a browser-agent system can complete 812 long-horizon tasks inside self-hosted replicas of functional websites. It checks the requested end state, so a result reflects the model, agent scaffold, browser interface, action budget, and evaluator together—not the base model alone. 2 models in the ModelScale catalog have a published value.
Each point is a model with a published WebArena value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
2 models with a published WebArena 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 | End-state task success |
|---|---|---|---|
| 1 | NVIDIA | 50.86 | |
| 2 | NVIDIA | 50.25 |
Evidence key: Observed
Rows are ordered by the value WebArena: A Realistic Web Environment for Building Autonomous 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.
What the benchmark measures and how its value is published, from the source’s own record.
WebArena (WebArena Web Agent Benchmark) is an agentic benchmark published by WebArena: A Realistic Web Environment for Building Autonomous Agents. WebArena tests whether a browser-agent system can complete 812 long-horizon tasks inside self-hosted replicas of functional websites. It checks the requested end state, so a result reflects the model, agent scaffold, browser interface, action budget, and evaluator together—not the base model alone. Its evaluation set is described by the source as 812 long-horizon browser tasks. The source rates its difficulty as stateful multi-site browser work.
Each model's result is published by WebArena: A Realistic Web Environment for Building Autonomous Agents as end-state task success. ModelScale prints that value exactly as published, and never converts or rescales it. This page ranks the 2 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.