Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details

19 runs
# Model Score Cost Calls
1 GPT 5.5 (xhigh) 38.4% $10.67 99 trace →
2 GPT 5.5 (high) 29.4% $2.75 27 trace →
3 GPT 5.6 Sol (medium) 28.9% $0.90 13 trace →
4 Claude Opus 4.7 (xhigh) 24.0% $5.13 110 trace →
5 Gemini 3.6 Flash 22.8% $3.68 139 trace →
6 Gemini 3 Flash 20.2% $0.19 53 trace →
7 GPT 5.5 19.2% $1.27 16 trace →
8 Claude Opus 4.6 18.4% $14.43 260 trace →
9 Gemini 3.5 Flash 10.3% $3.77 91 trace →
10 GPT 5.4 mini 1.5% $0.04 7 trace →
11 GPT 5.6 Sol (xhigh) 0.8% $13.78 85 trace →
12 Claude Opus 4.8 (xhigh) 0.8% $17.60 134 trace →
13 GLM-5.2 0.8% $32.60 165 trace →
14 Claude Haiku 4.5 0.8% $0.38 90 trace →
15 Claude Opus 4.7 0.7% $2.54 76 trace →
16 Claude Sonnet 4.6 0.7% $38.31 461 trace →
17 GPT 5.4 0.7% $0.46 12 trace →
18 Gemini 3.1 Pro 0.7% $0.89 44 trace →
19 GPT 5 mini 0.7% $0.01 10 trace →

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