← Back to leaderboard  ·  Show all task instances

cheat/cheat

cheat allows you to create and view interactive cheatsheets on the command-line. It was designed to help remind *nix system administrators of options for commands that they use frequently, but not frequently enough to remember.

13,278 go
297
Generated Behavioral Tests
88.9%
Best Score
Muse Spark 1.3 (max)

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 Muse Spark 1.3 (max) 88.9% $11.97 622 trace →
2 Claude Opus 5 (xhigh) 86.2% $27.42 243 trace →
3 Muse Spark 1.3 (xhigh) 79.5% $1.57 226 trace →
4 GPT-5.6 Sol (xhigh) 78.1% $3.67 30 trace →
5 Gemini 3.7 Flash 74.1% $1.39 127 trace →
6 GPT 5.5 (xhigh) 71.7% $9.93 81 trace →
7 Claude Opus 4.8 (xhigh) 70.4% $16.65 145 trace →
8 GPT 5.5 (high) 66.7% $4.69 60 trace →
9 GLM-5.2 66.7% $26.43 250 trace →
10 Gemini 3.5 Flash 62.6% $6.83 275 trace →
11 Claude Opus 4.6 59.9% $5.80 198 trace →
12 Muse Spark 1.1 (xhigh) 59.3% $0.52 317 trace →
13 GPT 5.5 57.6% $0.95 14 trace →
14 GPT-5.6 Sol 50.8% $1.02 12 trace →
15 Claude Sonnet 4.6 50.5% $14.36 373 trace →
16 Claude Opus 4.7 49.2% $3.11 86 trace →
17 Gemini 3.6 Flash 47.1% $3.53 143 trace →
18 GPT 5.4 45.1% $0.40 10 trace →
19 Gemini 3.1 Pro 22.9% $1.20 70 trace →
20 Claude Haiku 4.5 22.6% $0.91 159 trace →
21 Claude Opus 4.7 (xhigh) 14.1% $16.68 242 trace →
22 GPT 5.4 mini 9.4% $0.04 7 trace →
23 GPT 5 mini 5.7% $0.03 14 trace →
24 Muse Spark 1.2 (xhigh) 3.0% $0.53 137 trace →
25 Gemini 3 Flash 3.0% $0.33 110 trace →

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