# WebVoyager

> A browser-agent benchmark for completing multi-step workflows on live websites.

Canonical page: https://benchlm.ai/benchmarks/webvoyager

- Category: [Agentic](/agentic)
- Last updated: September 21, 2026

## About WebVoyager

- Year: 2026
- Tasks: Live website workflows
- Format: Interactive browser-agent evaluation
- Difficulty: Multi-step web navigation
- Paper: [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo)

BenchLM stores WebVoyager as a display-only browser-agent benchmark reference outside the weighted ranking schema.

WebVoyager is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (2 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Fara1.5-27B](/models/fara-1-5-27b) | Microsoft | 89.3% |
| 2 | [Fara1.5-4B](/models/fara-1-5-4b) | Microsoft | 80.8% |

## FAQ

### What does WebVoyager measure?

A browser-agent benchmark for completing multi-step workflows on live websites.

### Which model scores highest on WebVoyager?

Fara1.5-27B by Microsoft currently leads with a score of 89.3% on WebVoyager.

### How many models are evaluated on WebVoyager?

2 AI models have been evaluated on WebVoyager on BenchLM.

### Does WebVoyager affect BenchLM's overall score?

Not directly. WebVoyager is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on WebVoyager

- [Fara1.5-27B vs Fara1.5-4B](/compare/fara-1-5-27b-vs-fara-1-5-4b)