WebArena-Verified Browser Agent Benchmark

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.

4 models

Higher is better.

1Muse Spark 1.1Meta69.0
2Qwen3.8 MaxAlibaba66.8
3Qwen3.8-27BAlibaba64.8
4LFM2.5-24B-A2BLiquid AI26.8

Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric: Deterministic end-state task success
Tasks: 812 verified tasks; separate 258-task Hard subset
Authors: Amine El Hattami, Megh Thakkar, Nicolas Chapados, Christopher Pal (2025)
Source: WebArena-Verified: A Fully Audited Benchmark for Web Agents ↗

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.