tarka/xcp

An extended `cp`

911 rs medium
1,184
Generated Behavioral Tests
99.5%
Best Score
Claude Opus 5 (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 5 (xhigh) 99.5% $50.85 289 trace →
2 GPT-5.6 Sol (xhigh) 98.1% $4.77 34 trace →
3 Claude Opus 4.8 (xhigh) 96.9% $8.45 87 trace →
4 Gemini 3.7 Flash 95.9% $1.22 122 trace →
5 GPT 5.5 (xhigh) 95.8% $6.37 62 trace →
6 Claude Opus 4.6 92.6% $5.01 138 trace →
7 Claude Sonnet 4.6 91.7% $8.99 330 trace →
8 Claude Opus 4.7 (xhigh) 91.4% $13.71 263 trace →
9 GPT 5.4 84.5% $0.28 10 trace →
10 Gemini 3.1 Pro 73.7% $0.72 42 trace →
11 GLM-5.2 39.5% $9.98 171 trace →
12 GPT 5.5 38.7% $1.33 18 trace →
13 Gemini 3.6 Flash 38.0% $2.84 136 trace →
14 Claude Opus 4.7 37.2% $2.57 85 trace →
15 GPT 5.4 mini 22.5% $0.04 18 trace →
16 Gemini 3 Flash 9.0% $0.24 57 trace →
17 GPT 5 mini 4.3% $0.02 16 trace →
18 Claude Haiku 4.5 0.0% $0.73 107 trace →
19 GPT 5.5 (high) n/a $1.95 25 trace →

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