sharkdp/bat

A cat(1) clone with wings.

58,487 rs
799
Generated Behavioral Tests
86.7%
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

21 runs
# Model Score Cost Calls
1 Claude Opus 5 (xhigh) 86.7% $89.82 356 trace →
2 GPT-5.6 Sol (xhigh) 70.2% $8.89 49 trace →
3 GLM-5.2 67.3% $79.93 361 trace →
4 Claude Opus 4.8 (xhigh) 63.8% $26.98 170 trace →
5 Claude Sonnet 4.6 62.2% $21.25 514 trace →
6 GPT 5.5 (xhigh) 61.5% $7.87 82 trace →
7 Gemini 3.7 Flash 55.4% $1.18 129 trace →
8 GPT 5.5 (high) 51.3% $5.73 54 trace →
9 Claude Opus 4.7 (xhigh) 43.9% $4.75 110 trace →
10 GPT 5.5 41.8% $1.25 18 trace →
11 Gemini 3.1 Pro 33.2% $1.72 109 trace →
12 Gemini 3 Flash 33.2% $0.24 83 trace →
13 Claude Opus 4.7 31.9% $1.16 48 trace →
14 Claude Haiku 4.5 28.0% $0.62 129 trace →
15 GPT 5 mini 28.0% $0.02 11 trace →
16 GPT 5.4 13.4% $0.26 9 trace →
17 GPT 5.4 mini 3.1% $0.03 8 trace →
18 Gemini 3.5 Flash 2.6% $6.37 164 trace →
19 Gemini 3.6 Flash 2.0% $5.70 143 trace →
20 GPT-5.6 Sol 2.0% $1.11 15 trace →
21 Claude Opus 4.6 0.0% $2.85 253 trace →

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