# Orcaflex Model Generator 3 Way Benchmark

> Sub-skill of orcaflex-model-generator: 3-Way Benchmark.

- Skill: `vamseeachanta/orcaflex-model-generator-3-way-benchmark` (Agent Skill)
- Install (CLI): `npx skillmds@latest add vamseeachanta/orcaflex-model-generator-3-way-benchmark`
- Raw SKILL.md: https://api.skillmd.com/api/skills/vamseeachanta/orcaflex-model-generator-3-way-benchmark/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: vamseeachanta (https://skillmd.com/u/vamseeachanta)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/vamseeachanta/orcaflex-model-generator-3-way-benchmark

---


# 3-Way Benchmark

## 3-Way Benchmark


The benchmark validates three paths produce equivalent results:

| Path | Source | Pipeline |
|------|--------|----------|
| **A (monolithic)** | `.dat` file | Load directly in OrcFxAPI |
| **B (spec-driven)** | `.dat` → `.yml` → extract → spec → generate → load | Full round-trip |
| **C (library-direct)** | `spec.yml` → generate → load | From hand-written spec |

```bash
uv run python scripts/benchmark_model_library.py --library-only --three-way --skip-mesh
```

Results (2026-02-10): All 5 library models converge on all 3 paths with 0.00% tension difference.