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 5.6 Sol (xhigh) 39.0% $6.67 39 trace →
2 GPT 5.5 (high) 17.2% $3.46 36 trace →
3 Gemini 3.6 Flash 16.0% $7.02 181 trace →
4 Claude Opus 4.8 (xhigh) 12.8% $17.95 146 trace →
5 GPT 5.5 11.9% $0.94 14 trace →
6 Claude Opus 4.7 (xhigh) 10.0% $8.27 154 trace →
7 Claude Sonnet 4.6 7.5% $48.10 684 trace →
8 Gemini 3 Flash 6.7% $0.24 70 trace →
9 Claude Haiku 4.5 6.1% $0.64 142 trace →
10 GPT 5.4 5.3% $0.36 9 trace →
11 Gemini 3.1 Pro 5.0% $0.74 39 trace →
12 GPT 5.4 mini 5.0% $0.03 7 trace →
13 GLM-5.2 3.8% $6.12 97 trace →
14 GPT 5.6 Sol (medium) 3.7% $1.32 17 trace →
15 Claude Opus 4.7 3.7% $0.47 22 trace →
16 GPT 5 mini 1.7% $0.09 35 trace →
17 GPT 5.5 (xhigh) 0.0% $4.39 41 trace →
18 Gemini 3.5 Flash 0.0% $4.95 163 trace →
19 Claude Opus 4.6 0.0% $2.60 218 trace →

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