Evaluation Output

Eval logs are saved to the logs/ directory by default.

By default, ct run eval exits non-zero and does not convert or upload the run if Inspect ends with an error or cancellation. Pass --no-fail-on-error only when sample errors should be retained without failing the command.

# Custom output location
uv run ct run eval --log-dir my-logs/ --run-name experiment1

Eval files use Inspect's .eval format and can be viewed with:

# Open in Inspect viewer
inspect view logs/my-eval.eval

# Convert a specific sample to one trajectory file
uv run ct traj make logs/my-eval.eval --sample-id <sample_id> --save-path ./trajectories/traj.json

# Batch convert multiple evals
uv run ct runs make logs/attack_eval/example.eval --save-dir ./trajectories/