riquito/tuc
When cut doesn't cut it
1,196
Generated Behavioral Tests
98.2%
Best Score
GPT 5.6 Sol (xhigh)
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) | 98.2% | $9.06 | 55 | trace → |
| 2 | |
GPT 5.5 (xhigh) | 96.1% | $12.77 | 105 | trace → |
| 3 |  |
Gemini 3.6 Flash | 95.5% | $4.35 | 155 | trace → |
| 4 |  |
Claude Opus 4.8 (xhigh) | 95.4% | $26.21 | 143 | trace → |
| 5 | |
Claude Opus 4.7 | 92.7% | $8.58 | 165 | trace → |
| 6 |  |
GLM-5.2 | 92.5% | $18.94 | 156 | trace → |
| 7 | |
Claude Opus 4.6 | 90.5% | $16.11 | 317 | trace → |
| 8 | |
GPT 5.5 (high) | 89.5% | $4.67 | 47 | trace → |
| 9 | |
Gemini 3.5 Flash | 88.8% | $5.80 | 220 | trace → |
| 10 | |
Claude Opus 4.7 (xhigh) | 88.6% | $15.11 | 188 | trace → |
| 11 | |
Claude Sonnet 4.6 | 88.1% | $16.19 | 506 | trace → |
| 12 | |
GPT 5.6 Sol (medium) | 85.0% | $0.88 | 14 | trace → |
| 13 | |
GPT 5.5 | 60.7% | $0.89 | 13 | trace → |
| 14 | |
Claude Haiku 4.5 | 58.9% | $0.94 | 182 | trace → |
| 15 | |
GPT 5.4 | 53.8% | $0.30 | 10 | trace → |
| 16 | |
GPT 5 mini | 37.0% | $0.02 | 14 | trace → |
| 17 | |
Gemini 3.1 Pro | 17.1% | $0.94 | 87 | trace → |
| 18 | |
Gemini 3 Flash | 1.5% | $0.28 | 82 | trace → |
| 19 | |
GPT 5.4 mini | 0.0% | $0.04 | 22 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run