← Back to leaderboard  ·  Show all task instances

astaxie/bat

Go implement CLI, cURL-like tool for humans

2,563 go easy
1,091
Generated Behavioral Tests
89.3%
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) 89.3% $35.99 209 trace →
2 Muse Spark 1.3 (xhigh) 86.3% $1.28 200 trace →
3 Muse Spark 1.3 (max) 86.1% $1.17 144 trace →
4 GPT-5.6 Sol (xhigh) 82.7% $5.35 40 trace →
5 Claude Opus 4.8 (xhigh) 82.4% $14.77 111 trace →
6 Muse Spark 1.1 (xhigh) 81.0% $0.24 162 trace →
7 GPT 5.5 (xhigh) 79.5% $5.83 49 trace →
8 GPT 5.5 79.4% $1.16 17 trace →
9 Gemini 3.7 Flash 79.1% $1.43 99 trace →
10 GPT 5.5 (high) 78.2% $2.19 21 trace →
11 Claude Opus 4.6 71.8% $9.63 188 trace →
12 GPT-5.6 Sol 71.6% $0.73 13 trace →
13 Claude Opus 4.7 (xhigh) 70.9% $13.25 132 trace →
14 Gemini 3.5 Flash 69.9% $5.97 142 trace →
15 Claude Opus 4.7 66.4% $4.95 126 trace →
16 Gemini 3 Flash 65.4% $0.29 85 trace →
17 Claude Sonnet 4.6 64.5% $18.12 365 trace →
18 Muse Spark 1.2 (xhigh) 63.8% $0.05 65 trace →
19 Gemini 3.6 Flash 62.1% $2.88 102 trace →
20 GLM-5.2 61.0% $12.53 137 trace →
21 GPT 5.4 58.9% $0.17 9 trace →
22 Gemini 3.1 Pro 50.5% $1.25 55 trace →
23 Claude Haiku 4.5 49.9% $0.58 88 trace →
24 GPT 5.4 mini 26.4% $0.04 8 trace →
25 GPT 5 mini 16.0% $0.01 9 trace →

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