johnkerl/miller
Miller is like awk, sed, cut, join, and sort for name-indexed data such as CSV, TSV, and tabular JSON
14,637
Generated Behavioral Tests
38.9%
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) | 38.9% | $5.60 | 36 | trace → |
| 2 |  |
GLM-5.2 | 29.2% | $37.93 | 347 | trace → |
| 3 |  |
Claude Opus 4.8 (xhigh) | 28.8% | $22.19 | 192 | trace → |
| 4 | |
GPT 5.6 Sol (medium) | 25.1% | $1.33 | 21 | trace → |
| 5 | |
Claude Opus 4.7 (xhigh) | 24.1% | $8.12 | 127 | trace → |
| 6 | |
GPT 5.5 (high) | 23.4% | $3.02 | 26 | trace → |
| 7 | |
Claude Opus 4.6 | 22.9% | $13.86 | 322 | trace → |
| 8 | |
Claude Opus 4.7 | 19.0% | $2.86 | 62 | trace → |
| 9 |  |
Gemini 3.6 Flash | 18.5% | $3.97 | 157 | trace → |
| 10 | |
GPT 5.5 | 16.9% | $1.02 | 15 | trace → |
| 11 | |
Gemini 3.5 Flash | 11.5% | $5.31 | 174 | trace → |
| 12 | |
Gemini 3 Flash | 11.5% | $0.20 | 58 | trace → |
| 13 | |
GPT 5.4 | 8.0% | $0.32 | 11 | trace → |
| 14 | |
Gemini 3.1 Pro | 4.9% | $0.95 | 59 | trace → |
| 15 | |
Claude Haiku 4.5 | 4.9% | $1.61 | 206 | trace → |
| 16 | |
GPT 5.4 mini | 4.7% | $0.02 | 8 | trace → |
| 17 | |
GPT 5 mini | 3.4% | $0.02 | 12 | trace → |
| 18 | |
GPT 5.5 (xhigh) | 0.0% | $5.15 | 60 | trace → |
| 19 | |
Claude Sonnet 4.6 | 0.0% | $5.77 | 286 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run