agourlay/zip-password-finder

Find the password of protected ZIP files.

534 rs medium
680
Generated Behavioral Tests
99.9%
Best Score
Claude Opus 4.8 (xhigh)

Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details

19 runs
# Model Score Cost Calls
1 Claude Opus 4.8 (xhigh) 99.9% $11.27 111 trace →
2 GPT 5.5 (xhigh) 98.7% $4.94 59 trace →
3 GPT 5.6 Sol (xhigh) 98.2% $3.19 33 trace →
4 Claude Opus 4.6 97.9% $3.51 129 trace →
5 Gemini 3.5 Flash 97.6% $4.35 192 trace →
6 GPT 5.5 (high) 97.4% $1.90 29 trace →
7 Claude Opus 4.7 97.4% $2.53 78 trace →
8 Gemini 3.6 Flash 96.5% $3.61 156 trace →
9 GPT 5.6 Sol (medium) 94.3% $0.88 21 trace →
10 Gemini 3.1 Pro 90.4% $1.16 86 trace →
11 GPT 5.5 90.3% $1.19 22 trace →
12 GLM-5.2 81.4% $13.21 111 trace →
13 Claude Opus 4.7 (xhigh) 79.4% $6.96 143 trace →
14 Claude Sonnet 4.6 79.1% $8.63 295 trace →
15 Gemini 3 Flash 72.9% $0.26 118 trace →
16 Claude Haiku 4.5 38.8% $0.53 94 trace →
17 GPT 5.4 mini 27.4% $0.05 9 trace →
18 GPT 5.4 27.2% $0.19 10 trace →
19 GPT 5 mini 5.4% $0.02 18 trace →

Click a row to replay how that model rebuilt this program, or the model name to open its full run