← Back to leaderboard  ·  Show all task instances

foriequal0/git-trim

Automatically trims your branches whose tracking remote refs are merged or stray

548 rs medium
509
Generated Behavioral Tests
86.8%
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) 86.8% $34.76 260 trace →
2 Muse Spark 1.3 (max) 85.7% $3.63 276 trace →
3 Muse Spark 1.3 (xhigh) 79.6% $1.66 293 trace →
4 GPT 5.5 (xhigh) 79.0% $7.04 59 trace →
5 GPT-5.6 Sol (xhigh) 78.6% $5.11 26 trace →
6 Claude Opus 4.8 (xhigh) 76.6% $25.96 184 trace →
7 GLM-5.2 75.2% $25.78 245 trace →
8 Gemini 3.7 Flash 71.7% $1.49 102 trace →
9 GPT 5.5 (high) 65.0% $2.95 41 trace →
10 Claude Opus 4.6 64.6% $11.85 321 trace →
11 Muse Spark 1.1 (xhigh) 61.5% $0.68 225 trace →
12 Muse Spark 1.2 (xhigh) 60.5% $0.59 166 trace →
13 Gemini 3.6 Flash 58.2% $5.85 151 trace →
14 Claude Sonnet 4.6 57.0% $13.30 334 trace →
15 Gemini 3.5 Flash 53.4% $4.22 141 trace →
16 Claude Opus 4.7 52.7% $2.67 82 trace →
17 GPT 5.5 50.7% $0.91 16 trace →
18 Claude Opus 4.7 (xhigh) 48.5% $4.29 114 trace →
19 GPT-5.6 Sol 47.3% $0.44 8 trace →
20 GPT 5.4 45.4% $0.28 15 trace →
21 Claude Haiku 4.5 41.1% $0.70 138 trace →
22 Gemini 3 Flash 38.9% $0.37 75 trace →
23 GPT 5.4 mini 11.6% $0.06 13 trace →
24 GPT 5 mini 10.4% $0.02 17 trace →
25 Gemini 3.1 Pro n/a $1.57 98 trace →

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