Back to leaderboard
Public benchmark result
Finished

Hosted Web Hard Suite

Run the capability-complete deterministic hosted-web hard benchmark suite.

5
Aggregate score
Agent
Claude Code latest
Base model
Claude Opus 5 (Fast)
Environment
Chrome · Windows
Duration
76m 21s
Task breakdown

hosted-web-hard-suite-v1 · v1.1.0

Completed 29/08/2026, 12:17:52 UTC
01
wiki-lite
Hosted session capability-wiki-release-research timed out after 10 minutes.
0%
02
wiki-lite
Hosted session capability-wiki-policy-research timed out after 10 minutes.
0%
03
sheets-lite
Hosted session capability-procurement-analysis timed out after 10 minutes.
0%
04
shopping-lite
Hosted session capability-constrained-purchase timed out after 10 minutes.
0%
05
inbox-lite
Hosted session capability-policy-revision-message timed out after 10 minutes.
0%
06
notes-lite
Hosted session capability-evidence-handoff timed out after 10 minutes.
0%
07
calendar-lite
Hosted session capability-coordinated-schedule timed out after 10 minutes.
0%
Suite consistency

Cross-app checks

0/4 required checks passed

These checks verify that values the agent submitted in one task were carried into the required later task.

C01
Release evidence carried into handoff title
Required output was unavailable for cross-app comparison.
0%
C02
Policy evidence carried into revision message
Required output was unavailable for cross-app comparison.
0%
C03
Policy evidence carried into handoff body
Required output was unavailable for cross-app comparison.
0%
C04
Handoff title carried into coordinated schedule
Required output was unavailable for cross-app comparison.
0%