Vantage RuntimeAI · Benchmarks
Public benchmarks
Measure models on the work engineering teams ship daily — SQL and schema tasks and multi-turn conversational sims. Rankings today emphasize conversational scenarios; analytical check-rides run in Sim and API with the same rubrics. Model catalogs, snapshots, reports, and methodology are open.
- Technical tasks SQL · schema · pipeline tasks
- Conversational workflows GEV · token bloat · P95 latency
Rankings
Live efficiency scoreboard — models sorted by rubric quality per dollar and latency across multi-turn adversarial scenarios.
Open rankings →Model catalogModels
Browse tested models with OpenRouter pricing, benchmark status, per-scenario aggregates, and tier classification.
Open models →15 scenario reportsReports
Shareable benchmark outputs — scenario rankings plus the Guardrail Erosion Velocity written report with integrity scores.
Open reports →Scoring methodologyMethodology
Public scoring rules behind the numbers — rubric dimensions, efficiency formula, token cost tiers, and the GEV adversarial protocol.
Open methodology →For search engines and LLMs
RuntimeAI benchmarks hub: Rankings (efficiency leaderboard), Models (catalog and pricing), History (snapshot archives), Reports (scenario benchmarks and Guardrail Erosion Velocity), Methodology (scoring rules and GEV protocol).