agents benchmark
WebVoyager
WebVoyager evaluates an agent's ability to navigate and complete tasks on real websites by perceiving page screenshots and executing browser actions.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
WebVoyager Ranking
Higher score ranks better on this benchmark.
| 01 | ZA | 88.5% | 100.0% | 1 | C |
WebVoyager Highlights
The leading models and scores on this benchmark.
What is WebVoyager?
What WebVoyager measures and how its scores work.
WebVoyager evaluates an agent's ability to navigate and complete tasks on real websites by perceiving page screenshots and executing browser actions.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- WebVoyager
- Modality
- multimodal
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- webvoyager|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about WebVoyager.
Which model scores highest on WebVoyager?
GLM-5V-Turbo is currently ranked first with 88.5%.
What does WebVoyager measure?
WebVoyager evaluates an agent's ability to navigate and complete tasks on real websites by perceiving page screenshots and executing browser actions.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.