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) 98.1% $4.58 35 trace →
2 Claude Opus 4.8 (xhigh) 98.1% $8.26 93 trace →
3 Gemini 3.5 Flash 98.1% $3.59 145 trace →
4 GPT 5.5 (xhigh) 97.8% $5.97 49 trace →
5 Claude Opus 4.7 97.5% $3.88 84 trace →
6 Claude Opus 4.7 (xhigh) 96.8% $6.88 119 trace →
7 GLM-5.2 95.8% $7.54 183 trace →
8 GPT 5.5 (high) 95.1% $2.65 34 trace →
9 Claude Opus 4.6 94.9% $5.68 171 trace →
10 Gemini 3.6 Flash 93.7% $2.17 111 trace →
11 GPT 5.5 92.4% $1.06 15 trace →
12 Claude Sonnet 4.6 92.3% $4.51 213 trace →
13 Gemini 3.1 Pro 90.6% $2.22 103 trace →
14 GPT 5.6 Sol (medium) 88.4% $0.44 9 trace →
15 Gemini 3 Flash 51.3% $0.47 88 trace →
16 GPT 5.4 11.9% $0.23 10 trace →
17 GPT 5 mini 9.1% $0.03 18 trace →
18 Claude Haiku 4.5 8.3% $0.99 148 trace →
19 GPT 5.4 mini 0.2% $0.05 16 trace →

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