← Back to leaderboard  ·  Show all task instances

FiloSottile/age

A simple, modern and secure encryption tool (and Go library) with small explicit keys, no config options, and UNIX-style composability.

22,077 go
676
Generated Behavioral Tests
92.0%
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) 92.0% $46.45 218 trace →
2 Claude Opus 4.8 (xhigh) 76.0% $27.10 158 trace →
3 GPT-5.6 Sol (xhigh) 70.3% $5.79 39 trace →
4 Gemini 3.6 Flash 65.1% $6.50 183 trace →
5 Gemini 3.7 Flash 63.9% $1.73 124 trace →
6 Claude Sonnet 4.6 63.5% $43.00 547 trace →
7 Claude Opus 4.6 60.9% $13.80 210 trace →
8 GPT 5.5 (high) 60.5% $6.36 60 trace →
9 GLM-5.2 56.2% $37.63 246 trace →
10 GPT 5.5 (xhigh) 54.9% $7.10 66 trace →
11 Muse Spark 1.2 (xhigh) 51.3% $1.79 337 trace →
12 GPT-5.6 Sol 49.7% $1.50 22 trace →
13 Gemini 3.1 Pro 49.3% $1.41 100 trace →
14 GPT 5.5 38.5% $1.07 15 trace →
15 Gemini 3.5 Flash 14.8% $3.96 115 trace →
16 Muse Spark 1.3 (xhigh) 13.9% $20.65 989 trace →
17 Claude Opus 4.7 13.9% $1.05 37 trace →
18 Muse Spark 1.3 (max) 12.9% $19.33 547 trace →
19 Claude Haiku 4.5 8.9% $0.91 156 trace →
20 GPT 5.4 8.6% $0.47 14 trace →
21 Gemini 3 Flash 3.1% $0.22 66 trace →
22 GPT 5.4 mini 0.3% $0.04 8 trace →
23 GPT 5 mini 0.1% $0.02 13 trace →
24 Claude Opus 4.7 (xhigh) 0.0% $4.35 65 trace →
25 Muse Spark 1.1 (xhigh) 0.0% $0.77 315 trace →

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