mikefarah/yq
yq is a portable command-line YAML, JSON, XML, CSV, TOML, HCL and properties processor
2,000
Generated Behavioral Tests
49.9%
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) | 49.9% | $4.21 | 29 | trace → |
| 2 |  |
GLM-5.2 | 44.0% | $25.03 | 183 | trace → |
| 3 |  |
Claude Sonnet 4.6 | 39.5% | $35.51 | 532 | trace → |
| 4 | |
Claude Opus 4.8 (xhigh) | 38.9% | $16.89 | 113 | trace → |
| 5 | |
GPT 5.5 (xhigh) | 37.5% | $9.50 | 87 | trace → |
| 6 | |
GPT 5.5 (high) | 29.6% | $2.60 | 32 | trace → |
| 7 | |
GPT 5.6 Sol (medium) | 27.4% | $1.63 | 22 | trace → |
| 8 | |
Claude Opus 4.7 (xhigh) | 16.5% | $5.49 | 92 | trace → |
| 9 | |
Claude Haiku 4.5 | 16.0% | $1.55 | 183 | trace → |
| 10 | |
GPT 5.5 | 14.5% | $1.00 | 13 | trace → |
| 11 |  |
Gemini 3.5 Flash | 14.4% | $2.45 | 76 | trace → |
| 12 | |
Claude Opus 4.7 | 11.5% | $1.28 | 38 | trace → |
| 13 | |
Gemini 3.1 Pro | 10.3% | $1.02 | 60 | trace → |
| 14 | |
GPT 5.4 | 6.9% | $0.76 | 20 | trace → |
| 15 | |
GPT 5.4 mini | 5.1% | $0.02 | 6 | trace → |
| 16 | |
GPT 5 mini | 4.0% | $0.02 | 8 | trace → |
| 17 | |
Gemini 3.6 Flash | 1.1% | $4.68 | 144 | trace → |
| 18 | |
Gemini 3 Flash | 1.1% | $0.19 | 65 | trace → |
| 19 | |
Claude Opus 4.6 | 0.0% | $2.85 | 217 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run