# Online-Mind2Web (GitHub snapshot pilot) evaluation

Run: online-mind2web-codex-playwright-20260916
Source version: bab3fc3f1bff5b42c0624c073b68ddf9ad651d91
Primary evaluator: rubric
Declared grading contract SHA-256: 0ff5b01ba6f9e9a34b345cb2f62ec14e859ebbb6ad1f1188422c935356b544d3

Actual GKE execution; exported from retained task receipts without rerunning the tasks. Missing selected tasks remain in the denominator.

## Codex + Playwright

| Site | Selected | Completed | Native pass/graded | Rubric pass/graded | Vision pass/graded | Mean latency |
| --- | ---: | ---: | ---: | ---: | ---: | ---: |
| jobs.chronicle.com | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 1/1 (100.0%) | 152.76s (1/1 measured) |
| www.adoptapet.com | 1 | 1 | 0/0 (incomplete) | 0/1 (0.0%) | 0/1 (0.0%) | 42.39s (1/1 measured) |
| www.bestbuy.com | 2 | 0 | 0/0 (incomplete) | 0/0 (incomplete) | 0/0 (incomplete) | 334.71s (2/2 measured) |
| www.fedex.com | 1 | 1 | 0/0 (incomplete) | 0/1 (0.0%) | 0/1 (0.0%) | 43.49s (1/1 measured) |
| www.google.com | 1 | 1 | 0/0 (incomplete) | 0/1 (0.0%) | 0/1 (0.0%) | 112.20s (1/1 measured) |
| www.ikea.com | 1 | 0 | 0/0 (incomplete) | 0/0 (incomplete) | 0/0 (incomplete) | 314.16s (1/1 measured) |
| www.microcenter.com | 1 | 1 | 0/0 (incomplete) | 0/1 (0.0%) | 0/1 (0.0%) | 60.38s (1/1 measured) |
| www.target.com | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 0/1 (0.0%) | 319.21s (1/1 measured) |
| www.theweathernetwork.com | 1 | 1 | 0/0 (incomplete) | 1/1 (100.0%) | 0/1 (0.0%) | 115.19s (1/1 measured) |
| Overall | 10 | 7 | 0/0 (incomplete) | 3/7 (incomplete) | 1/7 (incomplete) | 182.92s (10/10 measured) |