# Solver Benchmark Programmatic Usage

> Sub-skill of solver-benchmark: Programmatic Usage.

- Skill: `vamseeachanta/solver-benchmark-programmatic-usage` (Agent Skill)
- Install (CLI): `npx skillmds@latest add vamseeachanta/solver-benchmark-programmatic-usage`
- Raw SKILL.md: https://api.skillmd.com/api/skills/vamseeachanta/solver-benchmark-programmatic-usage/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: vamseeachanta (https://skillmd.com/u/vamseeachanta)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/vamseeachanta/solver-benchmark-programmatic-usage

---


# Programmatic Usage

## Programmatic Usage


```python
from pathlib import Path
from scripts.benchmark.run_3way_benchmark import run_benchmark

# Run benchmark
result = run_benchmark(
    spec_path=Path("specs/modules/benchmark/unit_box_spec.yml"),
    output_dir=Path("benchmark_output/unit_box"),
    solvers=["orcawave", "aqwa", "bemrosetta"],
    dry_run=False,
)

# Check results
print(f"Success: {result.success}")
for name, sr in result.solver_results.items():
    print(f"  {name}: {sr.status}")

if result.benchmark_result and result.benchmark_result.report:
    print(f"Consensus: {result.benchmark_result.report.overall_consensus}")
```