Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Agent Task Performance on AgentDojo Travel

13.57Attack Success Rate

No Defense

-0.54283.12116.78510.4489Dec 21, 2024Feb 24, 2025May 1, 2025Jul 5, 2025Sep 9, 2025Nov 13, 2025Jan 18, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2024.12
13.57-5547.14
2024.12
11.4364.29--
2024.12
11.43-6564.29
2024.12
7.14-9072.14
2024.12
7.14-6052.14
2026.01
6.674-66.4
2024.12
5.71-9070
4.678-75.1
2024.12
3.57-7572.14
2.941-33.1
277-70.3
2026.01
1.673-70
2024.12
1.4372.86--
2024.12
1.43-8072.86
2024.12
0.71-6058.57
2024.12
0.71-5549.29
2024.12
067.86--
2024.12
072.14--
2024.12
070.71--
2024.12
077.14--
2024.12
0-3016.43
2024.12
0-7054.29
2024.12
0-2514.29
2026.01
073-73.7