Skip to content
VENKAI

Benchmarks

SME Benchmark v0.1

v0.1 — 2026-08-04

Every figure on this site names the command that reproduces it. This page is the methodology behind those commands — dataset, environment, and what isn't measured yet.

Dataset

damage_lite300: 455 injected-mutation cases against Venkai's own monorepo, 207 structurally in reach for damage. see_bench: a corpus of real symbols drawn from the same repository, not synthetic fixtures.

Environment

Runs offline, network disabled, against a single codebase (Venkai's own monorepo). No source material uploaded, no keys proxied through Venkai.

Benchmarks

What's compared

Two arms, both measured. A third is not — stated here rather than omitted.

SME-governed: the model describes an intent, SME resolves the anchor and applies a typed operation with rollback on failure.

Ungoverned: the model edits directly — full-file rewrite, unified diff, or raw shell write, with no anchor resolution or rollback.

Not yet measured: an LLM+RAG arm. No retrieval-augmented baseline has been run against this dataset — that comparison is v0.2, not a claim made today.

Benchmarks

Comparative Metrics Matrix

Agent alone vs. Agent + RAG vs. Agent + SME. Unmeasured cells explicitly display 'Not measured yet'.

MetricAgent AloneAgent + RAGAgent + SME
Token Usage100% baseline (147 t/edit)Not measured yet-95.9% (19 t/edit)
Cost100% baselineNot measured yet-95.9% payload cost
Execution TimeBaseline latencyNot measured yetUnder 1s overhead
Intent AccuracyNot measured yetNot measured yetNot measured yet
Regression RiskNot measured yetNot measured yetNot measured yet
Silent Damage Rate53.6%Not measured yet0.5% (Enforced)

Silent damage rate — autonomous AI agent execution

0.5% vs 53.6%

Silent damage rate (Venkai governed vs direct agent)

Direct un-governed agent execution(silent damage rate)53.6%
Venkai governed execution channel(verified & recorded)0.5%

$ python benchmarks/edit_damage_bench.py --limit 300 --offline

Measured 2026-08-04. Measures unverified modifications, unauthorized data accesses, and policy violations that execute without raising runtime exceptions. Figures are the silent rate among cases where damage was structurally reachable (455 cases run, 207 in reach) — a narrower, harder number than the raw silent rate across all cases. Full breakdown: /benchmarks/.

Secondary metric — token payload efficiency per edit

−95.9%

token reduction per execution

Model rewrites whole file / symbol(raw output tokens)17,553
Venkai governed semantic call(governed delta)713

$ python benchmarks/see_bench.py --limit 25

Measured 2026-08-03. Measured token output reduction when passing governed semantic diffs versus full-file re-generation.

Benchmarks

Roadmap for v0.2

A retrieval-augmented (RAG) comparison arm, and a corpus drawn from a codebase Venkai does not own.