← Back to leaderboard  ·  Show all task instances

sharkdp/fd

A simple, fast and user-friendly alternative to 'find'

42,668 rs medium
1,235
Generated Behavioral Tests
99.4%
Best Score
Claude Opus 5 (xhigh)

Results by Model

Hover for details · Click a model to open it · Drag to zoom the x-axis · Shift-drag to pan · The line marks the Pareto frontier (best score per cost)

Per-Model Results

25 runs
# Model Score Cost Calls
1 Claude Opus 5 (xhigh) 99.4% $89.62 407 trace →
2 Claude Opus 4.8 (xhigh) 93.9% $17.92 145 trace →
3 GLM-5.2 84.0% $50.45 305 trace →
4 GPT 5.5 (xhigh) 82.8% $8.84 94 trace →
5 Muse Spark 1.3 (xhigh) 82.6% $2.44 355 trace →
6 GPT-5.6 Sol (xhigh) 80.9% $5.52 40 trace →
7 Muse Spark 1.3 (max) 80.7% $5.28 339 trace →
8 GPT 5.5 (high) 80.2% $3.69 55 trace →
9 Gemini 3.7 Flash 79.5% $1.41 148 trace →
10 Claude Opus 4.7 78.1% $3.02 80 trace →
11 Muse Spark 1.2 (xhigh) 77.0% $1.40 155 trace →
12 Claude Opus 4.7 (xhigh) 76.4% $8.46 143 trace →
13 Claude Sonnet 4.6 74.8% $17.57 384 trace →
14 GPT-5.6 Sol 73.6% $1.27 17 trace →
15 GPT 5.5 72.6% $1.04 15 trace →
16 Gemini 3.6 Flash 67.0% $2.93 155 trace →
17 Gemini 3.1 Pro 54.5% $1.69 111 trace →
18 Gemini 3 Flash 48.9% $0.26 88 trace →
19 GPT 5.4 39.8% $0.28 12 trace →
20 Claude Haiku 4.5 39.7% $0.61 117 trace →
21 GPT 5.4 mini 3.6% $0.03 8 trace →
22 Muse Spark 1.1 (xhigh) 3.1% $0.56 174 trace →
23 GPT 5 mini 3.1% $0.05 16 trace →
24 Gemini 3.5 Flash 0.0% $3.92 134 trace →
25 Claude Opus 4.6 0.0% $1.07 183 trace →

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