yoav-lavi/melody
Melody is a language that compiles to regular expressions and aims to be more readable and maintainable
1,205
Generated Behavioral Tests
90.5%
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) | 90.5% | $31.56 | 154 | trace → |
| 2 | |
Claude Opus 4.7 (xhigh) | 87.4% | $17.22 | 215 | trace → |
| 3 |  |
GPT 5.5 (xhigh) | 84.9% | $4.22 | 56 | trace → |
| 4 | |
Claude Opus 4.7 | 78.9% | $5.37 | 135 | trace → |
| 5 | |
GPT 5.6 Sol (xhigh) | 78.3% | $2.19 | 21 | trace → |
| 6 |  |
GLM-5.2 | 78.2% | $22.03 | 278 | trace → |
| 7 | |
GPT 5.6 Sol (medium) | 77.4% | $1.03 | 16 | trace → |
| 8 | |
Claude Opus 4.6 | 74.4% | $12.05 | 325 | trace → |
| 9 | |
GPT 5.5 (high) | 71.5% | $3.79 | 54 | trace → |
| 10 |  |
Gemini 3.6 Flash | 66.4% | $3.80 | 180 | trace → |
| 11 | |
GPT 5.5 | 62.3% | $1.25 | 21 | trace → |
| 12 | |
Gemini 3 Flash | 62.3% | $0.28 | 138 | trace → |
| 13 | |
GPT 5.4 | 34.2% | $0.45 | 19 | trace → |
| 14 | |
Claude Haiku 4.5 | 31.4% | $0.98 | 131 | trace → |
| 15 | |
GPT 5.4 mini | 6.4% | $0.03 | 9 | trace → |
| 16 | |
Gemini 3.1 Pro | 6.1% | $2.10 | 203 | trace → |
| 17 | |
Claude Sonnet 4.6 | 3.4% | $16.67 | 502 | trace → |
| 18 | |
GPT 5 mini | 3.4% | $0.04 | 25 | trace → |
| 19 | |
Gemini 3.5 Flash | 0.0% | $5.11 | 280 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run