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)

25 runs
# Model Score Cost Calls
1 Claude Opus 5 (xhigh) 100.0% $11.96 110 trace →
2 GLM-5.2 98.9% $6.30 170 trace →
3 Gemini 3.6 Flash 98.6% $1.34 63 trace →
4 Claude Opus 4.6 98.2% $1.18 85 trace →
5 Muse Spark 1.3 (max) 91.2% $0.62 86 trace →
6 Muse Spark 1.3 (xhigh) 90.5% $0.19 85 trace →
7 GPT 5.5 (high) 90.5% $1.93 28 trace →
8 Muse Spark 1.1 (xhigh) 90.5% $0.22 84 trace →
9 GPT-5.6 Sol (xhigh) 87.7% $6.31 49 trace →
10 Claude Opus 4.8 (xhigh) 87.4% $5.31 63 trace →
11 Gemini 3.7 Flash 87.0% $0.38 67 trace →
12 Claude Opus 4.7 (xhigh) 87.0% $3.05 96 trace →
13 Gemini 3 Flash 86.7% $0.14 55 trace →
14 Muse Spark 1.2 (xhigh) 84.6% $0.08 48 trace →
15 GPT 5.5 (xhigh) 82.5% $2.08 32 trace →
16 Gemini 3.5 Flash 82.5% $0.91 66 trace →
17 GPT 5.5 82.5% $0.85 15 trace →
18 GPT 5.4 80.4% $0.15 10 trace →
19 GPT-5.6 Sol 76.5% $0.53 8 trace →
20 Claude Opus 4.7 76.1% $0.77 43 trace →
21 Gemini 3.1 Pro 73.7% $0.77 48 trace →
22 Claude Sonnet 4.6 71.6% $1.13 100 trace →
23 Claude Haiku 4.5 54.7% $0.53 108 trace →
24 GPT 5.4 mini 46.7% $0.16 255 trace →
25 GPT 5 mini 1.4% $0.02 16 trace →

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