← Back to leaderboard  ·  Show all task instances

gabotechs/dep-tree

Tool for helping developers keep their code bases clean and decoupled. It allows visualising a code base complexity using a 3d force-directed graph of files and the dependencies between them.

1,706 go medium
865
Generated Behavioral Tests
81.5%
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) 81.5% $56.43 337 trace →
2 Muse Spark 1.3 (max) 80.5% $6.62 478 trace →
3 GPT 5.5 (xhigh) 77.8% $9.65 99 trace →
4 Muse Spark 1.3 (xhigh) 77.1% $1.68 309 trace →
5 Claude Opus 4.8 (xhigh) 74.5% $17.28 163 trace →
6 Claude Sonnet 4.6 65.2% $38.29 585 trace →
7 Muse Spark 1.2 (xhigh) 64.0% $0.46 186 trace →
8 GPT 5.4 62.5% $0.30 8 trace →
9 GPT-5.6 Sol (xhigh) 60.5% $4.73 39 trace →
10 GPT 5.5 (high) 59.1% $4.51 55 trace →
11 Claude Opus 4.6 56.8% $12.17 245 trace →
12 GLM-5.2 55.0% $15.63 219 trace →
13 GPT 5.5 51.4% $1.29 21 trace →
14 Gemini 3.5 Flash 49.2% $5.84 181 trace →
15 Claude Opus 4.7 (xhigh) 38.8% $7.40 120 trace →
16 Claude Opus 4.7 37.1% $1.20 48 trace →
17 Gemini 3 Flash 35.0% $0.32 96 trace →
18 Gemini 3.1 Pro 18.0% $1.75 105 trace →
19 Muse Spark 1.1 (xhigh) 12.2% $0.37 137 trace →
20 GPT 5.4 mini 10.9% $0.03 9 trace →
21 GPT-5.6 Sol 10.9% $1.58 23 trace →
22 GPT 5 mini 9.0% $0.03 19 trace →
23 Gemini 3.6 Flash 0.0% $4.73 192 trace →
24 Gemini 3.7 Flash 0.0% $2.47 175 trace →
25 Claude Haiku 4.5 0.0% $0.86 154 trace →

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