pier-cli/pier
A CLI to organize and run short Unix shell scripts
692
Generated Behavioral Tests
97.5%
Best Score
Claude Opus 5 (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
21 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
Claude Opus 5 (xhigh) | 97.5% | $50.56 | 286 | trace → |
| 2 |  |
GPT 5.5 (xhigh) | 94.2% | $8.76 | 101 | trace → |
| 3 | |
Claude Opus 4.8 (xhigh) | 93.2% | $13.72 | 117 | trace → |
| 4 | |
Claude Opus 4.7 (xhigh) | 92.8% | $9.65 | 182 | trace → |
| 5 | |
GPT-5.6 Sol (xhigh) | 92.6% | $5.52 | 35 | trace → |
| 6 | |
GPT 5.5 (high) | 90.0% | $4.17 | 59 | trace → |
| 7 |  |
Gemini 3.7 Flash | 89.0% | $1.22 | 110 | trace → |
| 8 | |
GPT-5.6 Sol | 87.4% | $1.04 | 14 | trace → |
| 9 | |
Gemini 3.5 Flash | 85.4% | $3.85 | 183 | trace → |
| 10 |  |
GLM-5.2 | 84.4% | $18.21 | 237 | trace → |
| 11 | |
Claude Opus 4.6 | 83.8% | $9.16 | 245 | trace → |
| 12 | |
Claude Opus 4.7 | 83.4% | $3.71 | 83 | trace → |
| 13 | |
Gemini 3.6 Flash | 83.1% | $2.85 | 151 | trace → |
| 14 | |
GPT 5.5 | 76.3% | $1.20 | 18 | trace → |
| 15 | |
Gemini 3.1 Pro | 69.8% | $1.10 | 73 | trace → |
| 16 | |
GPT 5.4 | 57.5% | $0.52 | 13 | trace → |
| 17 | |
Gemini 3 Flash | 52.7% | $0.35 | 133 | trace → |
| 18 | |
Claude Haiku 4.5 | 45.7% | $0.88 | 115 | trace → |
| 19 | |
GPT 5.4 mini | 36.8% | $0.08 | 16 | trace → |
| 20 | |
GPT 5 mini | 14.6% | $0.03 | 29 | trace → |
| 21 | |
Claude Sonnet 4.6 | 2.9% | $4.77 | 211 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run