Back to playlists

Test

Coverage

medium 1 1 vulnerability total

Runs

Compare how tools did on this playlist: challenges solved against time, by model and agent count, plus recall, chain progress and cost across runs.

Challenges solved vs. time to finish the playlist Best: effractor, 1/1 solved in 3m 57s
Agents not reported
0101m2m3m4m5mTime to finish the playlist (wall clock)Challenges solvedeffractoreffractor

Recall

0%
0%
0%
100%
effractorrun3run4run5

F1 score

0%
0%
0%
100%
effractorrun3run4run5

Stages reached

0/0
0/0
0/0
0/0
effractorrun3run4run5

Vulnerabilities captured

0/1
0/1
0/1
1/1
effractorrun3run4run5

Duration

16s
17s
16s
3m 57s
effractorrun3run4run5

Cost

n/a
n/a
n/a
n/a
effractorrun3run4run5
RunToolModelsAgentsConcurrencyWhenDurationSolvedRecallF1CapturedStagesCostScorerStatus
run5effractorn/an/a1Aug 29, 07:40 PM3m 57s1/1100%100%1/10/0n/av1 completed
run4effractorn/an/a1Aug 29, 07:40 PM16s0/10%0%0/10/0n/av1 completed
run3effractorn/an/a1Aug 29, 07:38 PM17s0/10%0%0/10/0n/av1 completed
effractoreffractorn/an/a1Aug 29, 04:48 PM16s0/10%0%0/10/0n/av1 completed

Challenges run in this order

  1. 1 Generic Web #1 medium web 1 vulnerability