skeema/skeema
Declarative pure-SQL schema management for MySQL and MariaDB
1,708
Generated Behavioral Tests
79.7%
Best Score
GPT 5.5 (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
19 runs| # | Model | Score | Cost | Calls | ||
|---|---|---|---|---|---|---|
| 1 |  |
GPT 5.5 (xhigh) | 79.7% | $9.34 | 94 | trace → |
| 2 |  |
GLM-5.2 | 78.8% | $26.80 | 235 | trace → |
| 3 | |
GPT 5.5 (high) | 78.5% | $4.82 | 55 | trace → |
| 4 |  |
Claude Sonnet 4.6 | 76.5% | $16.73 | 416 | trace → |
| 5 |  |
Gemini 3.6 Flash | 75.2% | $3.07 | 120 | trace → |
| 6 | |
Claude Opus 4.6 | 74.9% | $7.91 | 269 | trace → |
| 7 | |
Gemini 3.5 Flash | 72.4% | $4.08 | 156 | trace → |
| 8 | |
Claude Opus 4.8 (xhigh) | 72.1% | $9.97 | 103 | trace → |
| 9 | |
GPT 5.5 | 61.2% | $1.42 | 21 | trace → |
| 10 | |
Claude Opus 4.7 | 57.3% | $1.47 | 63 | trace → |
| 11 | |
Claude Opus 4.7 (xhigh) | 56.7% | $12.76 | 161 | trace → |
| 12 | |
Gemini 3 Flash | 54.1% | $0.58 | 114 | trace → |
| 13 | |
Gemini 3.1 Pro | 53.2% | $0.96 | 77 | trace → |
| 14 | |
Claude Haiku 4.5 | 44.5% | $0.55 | 72 | trace → |
| 15 | |
GPT 5.6 Sol (xhigh) | 35.3% | $5.51 | 46 | trace → |
| 16 | |
GPT 5.6 Sol (medium) | 27.2% | $1.07 | 18 | trace → |
| 17 | |
GPT 5 mini | 23.8% | $0.03 | 23 | trace → |
| 18 | |
GPT 5.4 mini | 18.6% | $0.02 | 8 | trace → |
| 19 | |
GPT 5.4 | 3.1% | $0.41 | 16 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run