tomnomnom/gron
Make JSON greppable!
224
Generated Behavioral Tests
94.2%
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) | 94.2% | $4.09 | 36 | trace → |
| 2 |  |
Claude Opus 4.7 | 89.7% | $9.93 | 206 | trace → |
| 3 | |
Claude Opus 4.8 (xhigh) | 88.8% | $8.86 | 84 | trace → |
| 4 | |
Claude Opus 4.7 (xhigh) | 88.8% | $14.90 | 217 | trace → |
| 5 |  |
GLM-5.2 | 88.4% | $15.47 | 183 | trace → |
| 6 | |
Claude Opus 4.6 | 87.5% | $15.33 | 358 | trace → |
| 7 | |
GPT 5.5 (high) | 87.1% | $2.70 | 44 | trace → |
| 8 | |
GPT 5.5 (xhigh) | 85.7% | $4.82 | 46 | trace → |
| 9 |  |
Gemini 3.5 Flash | 85.3% | $3.63 | 153 | trace → |
| 10 | |
Claude Sonnet 4.6 | 83.9% | $14.17 | 459 | trace → |
| 11 | |
Gemini 3.6 Flash | 83.0% | $4.65 | 161 | trace → |
| 12 | |
Gemini 3 Flash | 78.6% | $0.31 | 121 | trace → |
| 13 | |
GPT 5.5 | 77.7% | $1.19 | 25 | trace → |
| 14 | |
GPT 5.6 Sol (medium) | 77.2% | $1.01 | 15 | trace → |
| 15 | |
Gemini 3.1 Pro | 71.0% | $1.56 | 177 | trace → |
| 16 | |
Claude Haiku 4.5 | 70.1% | $0.69 | 107 | trace → |
| 17 | |
GPT 5.4 | 58.0% | $0.36 | 13 | trace → |
| 18 | |
GPT 5 mini | 22.3% | $0.03 | 11 | trace → |
| 19 | |
GPT 5.4 mini | 20.1% | $0.03 | 10 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run