anordal/shellharden
The corrective bash syntax highlighter
1,095
Generated Behavioral Tests
96.7%
Best Score
Claude Opus 4.8 (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 |  |
Claude Opus 4.8 (xhigh) | 96.7% | $63.32 | 271 | trace → |
| 2 |  |
GPT 5.6 Sol (xhigh) | 91.8% | $6.50 | 50 | trace → |
| 3 | |
GPT 5.5 (xhigh) | 88.2% | $11.50 | 93 | trace → |
| 4 | |
GPT 5.5 (high) | 87.1% | $4.26 | 42 | trace → |
| 5 | |
Claude Opus 4.7 (xhigh) | 82.8% | $11.64 | 179 | trace → |
| 6 | |
GPT 5.6 Sol (medium) | 81.2% | $0.47 | 13 | trace → |
| 7 |  |
Gemini 3.6 Flash | 80.2% | $11.64 | 216 | trace → |
| 8 | |
GPT 5.5 | 79.7% | $1.16 | 18 | trace → |
| 9 | |
Gemini 3.5 Flash | 78.4% | $3.14 | 117 | trace → |
| 10 |  |
GLM-5.2 | 75.1% | $37.58 | 280 | trace → |
| 11 | |
Claude Opus 4.7 | 72.0% | $1.99 | 69 | trace → |
| 12 | |
Gemini 3.1 Pro | 71.1% | $1.40 | 143 | trace → |
| 13 | |
GPT 5.4 | 63.3% | $0.16 | 9 | trace → |
| 14 | |
Gemini 3 Flash | 59.6% | $0.24 | 90 | trace → |
| 15 | |
Claude Haiku 4.5 | 54.4% | $0.96 | 147 | trace → |
| 16 | |
Claude Sonnet 4.6 | 42.9% | $74.50 | 840 | trace → |
| 17 | |
GPT 5.4 mini | 16.2% | $0.04 | 18 | trace → |
| 18 | |
GPT 5 mini | 7.2% | $0.03 | 14 | trace → |
| 19 | |
Claude Opus 4.6 | 0.0% | $2.13 | 256 | trace → |
Click a row to replay how that model rebuilt this program, or the model name to open its full run