# WebVoyager · 15-task Browser Use pilot evaluation

Run: webvoyager-browser-use-20260915-vision-20260916
Source version: 5a7896738c10bfb8b9edccce6bb0e0411f8ae569:69b19fd86c23f1a500244a3724e039aa7ca6a1223d03e11eb10e308d4f11c488
Primary evaluator: rubric
Declared grading contract SHA-256: 82db14ea2dc5d3458d75a485c7de1eb4eefad97fca0871ea20146a4c8f0cb006

Imported recorded evidence; not independently rerun by Blobfish. Missing selected tasks remain in the denominator.

## Browser Use v4

| Site | Selected | Completed | Native pass/graded | Rubric pass/graded | Vision pass/graded | Mean latency |
| --- | ---: | ---: | ---: | ---: | ---: | ---: |
| Allrecipes | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 0/1 (0.0%) | 41.48s (1/1 measured) |
| Amazon | 1 | 1 | 0/0 (incomplete) | 0/1 (0.0%) | 0/1 (0.0%) | 102.31s (1/1 measured) |
| Apple | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 0/1 (0.0%) | 92.15s (1/1 measured) |
| ArXiv | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 1/1 (100.0%) | 101.12s (1/1 measured) |
| BBC News | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 0/1 (0.0%) | 182.26s (1/1 measured) |
| Booking | 1 | 1 | 0/0 (incomplete) | 0/1 (0.0%) | 0/1 (0.0%) | 202.18s (1/1 measured) |
| Cambridge Dictionary | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 1/1 (100.0%) | 30.51s (1/1 measured) |
| Coursera | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 0/1 (0.0%) | 121.99s (1/1 measured) |
| ESPN | 1 | 1 | 0/0 (incomplete) | 0/1 (0.0%) | 0/1 (0.0%) | 60.69s (1/1 measured) |
| GitHub | 1 | 1 | 0/0 (incomplete) | 0/1 (0.0%) | 0/1 (0.0%) | 111.19s (1/1 measured) |
| Google Flights | 1 | 1 | 0/0 (incomplete) | 0/1 (0.0%) | 0/1 (0.0%) | 164.06s (1/1 measured) |
| Google Map | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 1/1 (100.0%) | 50.52s (1/1 measured) |
| Google Search | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 0/1 (0.0%) | 166.81s (1/1 measured) |
| Huggingface | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 0/1 (0.0%) | 96.58s (1/1 measured) |
| Wolfram Alpha | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 0/1 (0.0%) | 244.21s (1/1 measured) |
| Overall | 15 | 15 | 0/0 (incomplete) | 10/15 (66.7%) | 3/15 (20.0%) | 117.87s (15/15 measured) |