logical-reasoning / data /anthropic_metrics.csv
inflaton's picture
claude 0-shot
397a2fa
raw
history blame
190 Bytes
shots,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
0,claude-3-5-sonnet-20240620,claude-3-5-sonnet-20240620/shots-00,0.698,0.7933748867472142,0.698,0.73047417384539,1.0