WebVoyager
A browser-agent benchmark for completing multi-step workflows on live websites.
1 models
Higher is better.
- 1Fara1.5-27BMicrosoft89.3
About this benchmark
- Metric
- Interactive browser-agent evaluation
- Tasks
- Live website workflows
- Authors
- Z.AI (2026)
- Source
- GLM-5V-Turbo ↗
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.