Results by Model
Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details
Per-Model Results
21 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
GPT 5.5 (xhigh) | 21.6% | $11.63 | 87 | trace → |
| 2 | |
GPT 5.5 (high) | 20.8% | $3.57 | 39 | trace → |
| 3 |  |
Claude Opus 5 (xhigh) | 19.2% | $30.56 | 264 | trace → |
| 4 | |
GPT-5.6 Sol | 15.0% | $1.17 | 19 | trace → |
| 5 | |
GPT-5.6 Sol (xhigh) | 13.8% | $4.75 | 34 | trace → |
| 6 | |
Claude Opus 4.6 | 13.3% | $10.16 | 341 | trace → |
| 7 |  |
GLM-5.2 | 12.1% | $13.26 | 148 | trace → |
| 8 | |
Claude Opus 4.8 (xhigh) | 11.3% | $14.06 | 137 | trace → |
| 9 |  |
Gemini 3.7 Flash | 10.8% | $1.34 | 143 | trace → |
| 10 | |
Gemini 3 Flash | 10.3% | $0.20 | 72 | trace → |
| 11 | |
Claude Opus 4.7 | 8.7% | $1.07 | 43 | trace → |
| 12 | |
GPT 5.4 | 7.9% | $0.23 | 9 | trace → |
| 13 | |
Claude Haiku 4.5 | 7.2% | $0.92 | 121 | trace → |
| 14 | |
GPT 5.5 | 7.1% | $0.83 | 13 | trace → |
| 15 | |
Gemini 3.1 Pro | 5.6% | $0.91 | 57 | trace → |
| 16 | |
GPT 5.4 mini | 2.4% | $0.03 | 11 | trace → |
| 17 | |
GPT 5 mini | 2.4% | $0.05 | 20 | trace → |
| 18 | |
Gemini 3.6 Flash | 0.5% | $3.29 | 199 | trace → |
| 19 | |
Claude Opus 4.7 (xhigh) | 0.5% | $3.91 | 115 | trace → |
| 20 | |
Gemini 3.5 Flash | 0.0% | $5.04 | 178 | trace → |
| 21 | |
Claude Sonnet 4.6 | 0.0% | $3.96 | 395 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run