claude-flow
Version:
Ruflo - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration
17 lines • 633 B
TypeScript
/**
* GAIA Ensemble Pilot — ADR-139 5-question validation
*
* Runs 5 diverse GAIA L1 questions through the 2-model ensemble
* (claude-sonnet-4-6 + gemini-2.5-pro) and reports accuracy, cost, and
* projections. OpenRouter is skipped until credits are topped up.
*
* Usage:
* node dist/src/benchmarks/gaia-ensemble-pilot.js
* node dist/src/benchmarks/gaia-ensemble-pilot.js --models claude-sonnet-4-6,gemini-2.5-pro,openai/gpt-5
*
* Exit codes:
* 0 pilot passed (accuracy ≥ 3/5 AND projected 53Q cost ≤ $40)
* 1 pilot failed or cost exceeded
*/
export {};
//# sourceMappingURL=gaia-ensemble-pilot.d.ts.map