Stranger6667/jsonschema
A high-performance JSON Schema validator for Rust
2,932
Generated Behavioral Tests
57.1%
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) | 57.1% | $8.32 | 101 | trace → |
| 2 | |
GPT 5.6 Sol (xhigh) | 55.6% | $3.89 | 25 | trace → |
| 3 | |
GPT 5.5 (high) | 55.1% | $2.99 | 37 | trace → |
| 4 |  |
GLM-5.2 | 52.6% | $28.79 | 362 | trace → |
| 5 |  |
Claude Opus 4.8 (xhigh) | 52.2% | $17.30 | 124 | trace → |
| 6 |  |
Gemini 3.5 Flash | 51.9% | $4.95 | 150 | trace → |
| 7 | |
Claude Opus 4.6 | 51.7% | $8.76 | 233 | trace → |
| 8 | |
GPT 5.6 Sol (medium) | 51.5% | $0.64 | 15 | trace → |
| 9 | |
Claude Opus 4.7 (xhigh) | 48.7% | $2.43 | 56 | trace → |
| 10 | |
Gemini 3.6 Flash | 48.0% | $3.54 | 122 | trace → |
| 11 | |
GPT 5.5 | 47.6% | $1.07 | 20 | trace → |
| 12 | |
Gemini 3 Flash | 40.9% | $0.17 | 80 | trace → |
| 13 | |
Claude Haiku 4.5 | 36.3% | $0.45 | 113 | trace → |
| 14 | |
GPT 5.4 mini | 16.8% | $0.05 | 15 | trace → |
| 15 | |
GPT 5 mini | 15.6% | $0.02 | 12 | trace → |
| 16 | |
Claude Opus 4.7 | 0.2% | $2.18 | 61 | trace → |
| 17 | |
Claude Sonnet 4.6 | 0.2% | $15.32 | 406 | trace → |
| 18 | |
GPT 5.4 | 0.2% | $0.18 | 10 | trace → |
| 19 | |
Gemini 3.1 Pro | 0.2% | $0.47 | 33 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run