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 Claude Opus 4.8 (xhigh) 84.1% $15.68 136 trace →
2 GPT 5.6 Sol (xhigh) 81.4% $4.78 39 trace →
3 GLM-5.2 76.9% $30.57 214 trace →
4 GPT 5.5 (xhigh) 76.4% $7.07 70 trace →
5 Gemini 3.6 Flash 73.6% $3.64 162 trace →
6 Gemini 3.5 Flash 73.0% $3.64 147 trace →
7 GPT 5.6 Sol (medium) 71.3% $0.84 15 trace →
8 GPT 5.5 (high) 71.0% $2.11 22 trace →
9 Claude Opus 4.6 66.8% $9.89 307 trace →
10 Claude Opus 4.7 61.7% $3.13 73 trace →
11 GPT 5.5 54.0% $0.74 13 trace →
12 GPT 5.4 49.1% $0.38 14 trace →
13 Gemini 3.1 Pro 46.4% $1.10 96 trace →
14 Claude Haiku 4.5 25.2% $1.70 207 trace →
15 Gemini 3 Flash 14.9% $0.26 109 trace →
16 Claude Opus 4.7 (xhigh) 3.4% $8.71 175 trace →
17 GPT 5.4 mini 3.4% $0.03 12 trace →
18 Claude Sonnet 4.6 3.0% $12.60 413 trace →
19 GPT 5 mini 2.9% $0.01 14 trace →

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