wintermute-cell/ngrrram
A TUI tool to help you type faster and learn new layouts. Includes a free cat.
303
Generated Behavioral Tests
99.7%
Best Score
Claude Opus 4.8 (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 |  |
Claude Opus 4.8 (xhigh) | 99.7% | $21.03 | 137 | trace → |
| 2 |  |
GPT 5.6 Sol (xhigh) | 99.3% | $8.30 | 69 | trace → |
| 3 | |
GPT 5.5 (xhigh) | 97.0% | $8.86 | 68 | trace → |
| 4 | |
GPT 5.5 | 96.7% | $1.51 | 25 | trace → |
| 5 | |
GPT 5.6 Sol (medium) | 95.0% | $1.26 | 20 | trace → |
| 6 |  |
Gemini 3.6 Flash | 92.1% | $6.41 | 163 | trace → |
| 7 | |
GPT 5.5 (high) | 85.8% | $2.88 | 32 | trace → |
| 8 | |
Claude Opus 4.7 | 84.5% | $22.00 | 318 | trace → |
| 9 |  |
GLM-5.2 | 84.2% | $33.79 | 246 | trace → |
| 10 | |
Claude Opus 4.7 (xhigh) | 73.6% | $31.63 | 326 | trace → |
| 11 | |
Gemini 3.5 Flash | 68.6% | $4.27 | 108 | trace → |
| 12 | |
Gemini 3 Flash | 62.0% | $0.33 | 72 | trace → |
| 13 | |
Claude Sonnet 4.6 | 58.1% | $39.89 | 576 | trace → |
| 14 | |
Claude Opus 4.6 | 47.5% | $11.82 | 194 | trace → |
| 15 | |
Claude Haiku 4.5 | 43.9% | $0.60 | 124 | trace → |
| 16 | |
GPT 5.4 | 31.0% | $0.28 | 10 | trace → |
| 17 | |
GPT 5.4 mini | 31.0% | $0.02 | 7 | trace → |
| 18 | |
GPT 5 mini | 27.7% | $0.01 | 9 | trace → |
| 19 | |
Gemini 3.1 Pro | 13.5% | $4.25 | 164 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run