Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Malicious Command Interception on OpenClaw 1.0 (test)
Loading...
83
Defense Rate
Claude Opus 4.6
14.36
32.18
50
67.82
Mar 11, 2026
Defense Rate
Ranking Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Defense Rate
Ranking Score
Claude Opus 4.6
LLM Backend=Claude Opu...
2026.03
83
-
Qwen3 Max
LLM Backend=Qwen3 Max,...
2026.03
68.1
-
GPT 5.3 Codex
LLM Backend=GPT 5.3 Co...
2026.03
48.9
-
Kimi K2.5
LLM Backend=Kimi K2.5,...
2026.03
27.7
-
Gemini 3.1 Pro
LLM Backend=Gemini 3.1...
2026.03
23.4
-
DeepSeek V3.2
LLM Backend=DeepSeek V...
2026.03
17
-
Feedback
Search any
task
Search any
task