Benchmark browser

Rows are pre-aggregated by task, target, prompt variant, MCP-instruction mode, context, arm, and restriction. Numeric values show median (p50), IQR, p90, maximum, and sample count. Boolean checks show pass counts and success rates. Filters apply to these summary groups; per-run observations remain available on their run pages.

Requirement met Expected semantic tools used Model Prompt variant Semedit restriction MCP instructions

Loading benchmark results…

Baseline vs semedit

Comparison evaluates baseline and semedit values within each restriction policy, target, and context group. Negative changes mark improvements for these lower-is-better metrics; positive changes mark degradations.

Requirement met Expected semantic tools used Model Prompt variant Semedit restriction MCP instructions

Benchmark aggregates