Use PyGhidra with jq for JSON output processing.
Performance
| Model | Pass Rate | Runs | Avg Cost | Avg Time |
|---|---|---|---|---|
| kimi-k2.5 | 100% | | $0.05 | 11m |
| claude-sonnet-4.5 | 100% | | $0.19 | 9m |
| gpt-5 | 100% | | $0.26 | 11m |
| claude-opus-4.5 | 100% | | $0.27 | 7m |
| claude-opus-4.6 | 100% | | $0.30 | 7m |
| gemini-3-pro-preview | 100% | | $0.37 | 9m |
| glm-4.7 | 67% | | $0.24 | 22m |
| gpt-5.2-codex | 67% | | $0.42 | 13m |
| gpt-5.2 | 67% | | $0.44 | 16m |
| grok-4 | 67% | | $0.74 | 23m |
| gemini-3-flash-preview | 33% | | $0.05 | 8m |
| claude-haiku-4.5 | 33% | | $0.38 | 22m |
| grok-4.1-fast | 0% | | $0.05 | 28m |
| deepseek-v3.2 | 0% | | $0.05 | 30m |
| gemini-2.5-pro | 0% | | $0.62 | 20m |
| claude-sonnet-4 | 0% | | $0.62 | 12m |
All product names, logos, and brands (™/®) are the property of their respective owners; they're used here solely for identification and comparison, and their use does not imply affiliation, endorsement, or sponsorship.