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
19 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
GPT 5.6 Sol (xhigh) | 56.6% | $8.43 | 57 | trace → |
| 2 | |
GPT 5.5 (high) | 46.8% | $4.19 | 46 | trace → |
| 3 | |
GPT 5.5 (xhigh) | 41.7% | $7.05 | 59 | trace → |
| 4 | |
GPT 5.6 Sol (medium) | 34.5% | $1.38 | 21 | trace → |
| 5 |  |
Claude Sonnet 4.6 | 33.9% | $19.38 | 343 | trace → |
| 6 | |
GPT 5.5 | 28.8% | $1.01 | 13 | trace → |
| 7 |  |
Gemini 3.5 Flash | 28.4% | $3.58 | 127 | trace → |
| 8 |  |
GLM-5.2 | 15.5% | $28.32 | 255 | trace → |
| 9 | |
Gemini 3.1 Pro | 14.9% | $1.39 | 106 | trace → |
| 10 | |
GPT 5.4 | 9.9% | $0.31 | 9 | trace → |
| 11 | |
Claude Opus 4.8 (xhigh) | 5.9% | $17.93 | 163 | trace → |
| 12 | |
Claude Opus 4.6 | 5.2% | $6.02 | 218 | trace → |
| 13 | |
Gemini 3 Flash | 4.8% | $0.19 | 65 | trace → |
| 14 | |
Claude Opus 4.7 (xhigh) | 2.8% | $2.95 | 62 | trace → |
| 15 | |
GPT 5 mini | 2.4% | $0.02 | 6 | trace → |
| 16 | |
GPT 5.4 mini | 2.2% | $0.04 | 7 | trace → |
| 17 | |
Claude Opus 4.7 | 1.2% | $0.60 | 35 | trace → |
| 18 | |
Gemini 3.6 Flash | 0.6% | $3.90 | 111 | trace → |
| 19 | |
Claude Haiku 4.5 | 0.0% | $1.10 | 157 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run