sclevine/yj
CLI - Convert between YAML, TOML, JSON, and HCL. Preserves map order.
767
Generated Behavioral Tests
98.6%
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) | 98.6% | $46.20 | 238 | trace → |
| 2 |  |
GPT-5.6 Sol (xhigh) | 87.1% | $8.00 | 57 | trace → |
| 3 |  |
GLM-5.2 | 84.9% | $29.51 | 289 | trace → |
| 4 |  |
Gemini 3.7 Flash | 83.2% | $1.69 | 154 | trace → |
| 5 | |
GPT 5.5 (xhigh) | 81.7% | $5.69 | 52 | trace → |
| 6 | |
Claude Opus 4.7 (xhigh) | 78.7% | $16.06 | 196 | trace → |
| 7 | |
Claude Opus 4.8 (xhigh) | 78.3% | $12.11 | 104 | trace → |
| 8 | |
Gemini 3.6 Flash | 77.1% | $3.74 | 153 | trace → |
| 9 | |
Gemini 3.5 Flash | 75.0% | $4.73 | 192 | trace → |
| 10 | |
Claude Opus 4.7 | 74.4% | $4.14 | 88 | trace → |
| 11 | |
GPT-5.6 Sol | 74.3% | $1.02 | 16 | trace → |
| 12 | |
GPT 5.5 (high) | 73.5% | $2.48 | 34 | trace → |
| 13 | |
GPT 5.5 | 66.5% | $0.79 | 15 | trace → |
| 14 | |
GPT 5.4 | 50.2% | $0.32 | 13 | trace → |
| 15 | |
Claude Haiku 4.5 | 46.3% | $1.61 | 184 | trace → |
| 16 | |
GPT 5 mini | 31.9% | $0.02 | 13 | trace → |
| 17 | |
Gemini 3.1 Pro | 12.3% | $1.40 | 85 | trace → |
| 18 | |
Claude Sonnet 4.6 | 2.0% | $25.56 | 730 | trace → |
| 19 | |
GPT 5.4 mini | 2.0% | $0.02 | 8 | trace → |
| 20 | |
Claude Opus 4.6 | 0.0% | $2.92 | 293 | trace → |
| 21 | |
Gemini 3 Flash | 0.0% | $0.23 | 112 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run