AI Safety Evaluation Datasets Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. aisa-group/EvalAwareBench Viewer • Updated May 25 • 103k • 299 • 7 aisa-group/instrumental-choices-agent-traces Updated 20 days ago • 544 • 1 aisa-group/ResearchArena-Trajectories Updated 4 days ago • 24.9k • 1
Agent Trajectories Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. aisa-group/ResearchArena-Trajectories Updated 4 days ago • 24.9k • 1 aisa-group/PostTrainBench-Trajectories Updated about 6 hours ago • 18.9k • 8 aisa-group/InferenceBench-Trajectories Updated Jun 21 • 184 • 3 aisa-group/instrumental-choices-agent-traces Updated 20 days ago • 544 • 1
AI Safety Evaluation Datasets Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. aisa-group/EvalAwareBench Viewer • Updated May 25 • 103k • 299 • 7 aisa-group/instrumental-choices-agent-traces Updated 20 days ago • 544 • 1 aisa-group/ResearchArena-Trajectories Updated 4 days ago • 24.9k • 1
Agent Trajectories Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. aisa-group/ResearchArena-Trajectories Updated 4 days ago • 24.9k • 1 aisa-group/PostTrainBench-Trajectories Updated about 6 hours ago • 18.9k • 8 aisa-group/InferenceBench-Trajectories Updated Jun 21 • 184 • 3 aisa-group/instrumental-choices-agent-traces Updated 20 days ago • 544 • 1
