← Back to leaderboard  ·  Show all task instances

shashwatah/jot

⚡Rapid note management for the terminal.

609 rs medium
752
Generated Behavioral Tests
99.7%
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) 99.7% $62.09 393 trace →
2 Muse Spark 1.3 (max) 99.5% $3.75 243 trace →
3 Muse Spark 1.3 (xhigh) 99.3% $0.89 169 trace →
4 Claude Opus 4.8 (xhigh) 98.7% $28.13 195 trace →
5 GPT 5.5 (xhigh) 97.1% $9.55 73 trace →
6 GPT-5.6 Sol (xhigh) 96.9% $2.68 26 trace →
7 Muse Spark 1.2 (xhigh) 96.3% $3.04 270 trace →
8 Muse Spark 1.1 (xhigh) 95.9% $0.27 130 trace →
9 GLM-5.2 95.3% $20.94 300 trace →
10 GPT 5.5 (high) 94.1% $3.55 46 trace →
11 Gemini 3.6 Flash 93.0% $4.14 138 trace →
12 Gemini 3.7 Flash 92.0% $1.19 128 trace →
13 GPT-5.6 Sol 89.8% $1.09 14 trace →
14 GPT 5.5 86.4% $0.94 15 trace →
15 Claude Opus 4.6 84.4% $8.70 216 trace →
16 Gemini 3.5 Flash 83.1% $5.85 253 trace →
17 Claude Opus 4.7 (xhigh) 79.4% $27.97 362 trace →
18 Gemini 3.1 Pro 77.4% $2.34 222 trace →
19 GPT 5.4 70.3% $0.52 14 trace →
20 Claude Opus 4.7 69.3% $6.83 182 trace →
21 Claude Sonnet 4.6 67.4% $9.27 374 trace →
22 Gemini 3 Flash 43.2% $0.45 166 trace →
23 Claude Haiku 4.5 37.8% $1.91 245 trace →
24 GPT 5.4 mini 7.4% $0.04 11 trace →
25 GPT 5 mini 3.9% $0.03 17 trace →

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