Benchmark

WebVoyager

WebVoyager evaluates an agent's ability to navigate and complete tasks on real websites by perceiving page screenshots and executing browser actions.

Modality
multimodal
Categories
agents, vision
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
GLM-5V-TurboZ.ai0.8852026-04-02evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.