sqlite/sqlite
Official Git mirror of the SQLite source tree
13,510
Generated Behavioral Tests
71.6%
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) | 71.6% | $14.62 | 155 | trace → | |
| 2 | GPT 5.5 (high) | 68.4% | $3.06 | 45 | trace → | |
| 3 | GLM-5.2 | 68.1% | $15.34 | 215 | trace → | |
| 4 | Gemini 3.6 Flash | 67.9% | $3.58 | 156 | trace → | |
| 5 | Claude Opus 4.7 | 67.0% | $1.08 | 37 | trace → | |
| 6 | GPT 5.6 Sol (medium) | 65.8% | $0.87 | 12 | trace → | |
| 7 | Claude Opus 4.7 (xhigh) | 64.5% | $2.48 | 68 | trace → | |
| 8 | GPT 5.5 | 63.7% | $1.69 | 30 | trace → | |
| 9 | Claude Sonnet 4.6 | 1.3% | $28.86 | 573 | trace → | |
| 10 | GPT 5.6 Sol (xhigh) | 1.3% | $8.47 | 46 | trace → | |
| 11 | Gemini 3.5 Flash | 1.0% | $6.54 | 277 | trace → | |
| 12 | Gemini 3 Flash | 0.9% | $0.19 | 74 | trace → | |
| 13 | Claude Opus 4.8 (xhigh) | 0.8% | $21.76 | 135 | trace → | |
| 14 | GPT 5.4 | 0.6% | $0.20 | 9 | trace → | |
| 15 | GPT 5.4 mini | 0.5% | $0.02 | 11 | trace → | |
| 16 | Gemini 3.1 Pro | 0.4% | $0.85 | 77 | trace → | |
| 17 | Claude Haiku 4.5 | 0.3% | $0.57 | 137 | trace → | |
| 18 | GPT 5 mini | 0.2% | $0.01 | 14 | trace → | |
| 19 | Claude Opus 4.6 | 0.0% | $4.54 | 274 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run