Benchmark run opencode-qwen36-iq4-xs-task004-20261004-1622

This page contains exactly the publishable benchmark observations recorded in run opencode-qwen36-iq4-xs-task004-20261004-1622; it does not select or aggregate them. Return to the run index or view aggregate metrics.

Interactive browser

Detailed observations

Empirical telemetry measuring wall-clock latency, token usage, tool turns, and compiler correctness when AI coding agents perform code modifications.

Every benchmark pairs Vanilla LLM (standard file editing tools) against Semedit MCP (deterministic AST compiler operations).

Benchmark Methodology & Transparency

• Reproducibility & Provenance: Self-contained txtar archives define test scenarios. Links below resolve to commit-anchored GitHub source files for published commits, or cryptographic SHA-256 fingerprints for uncommitted local fixtures.
• Model Cost: Tables report model-specific credit consumption where a target model has a declared schedule: (uncached input × input credits + cached input × cached credits + (reasoning + visible output) × output credits) / 1,000,000. Thinking tokens use the output rate. ADR-0043 defines the per-million-token credit rates.
• Multi-Level Correctness Oracle: Four validation levels evaluate each trial:
  1. Level 1 (Mutation Policy): Restricts file modifications strictly to authorized paths.
  2. Level 2 (AST Invariants): Compiler AST verification of required symbols, imports, and relative declaration ordering.
  3. Level 3 (Clean Build): Strict compilation validation with zero compiler or typecheck errors.
  4. Level 4 (Test Suite): Unit and integration test suite execution.
• Isolated Sandboxing: Each trial executes in an ephemeral directory with pristine git and module state.

Test case: task-04-insert-public

Target: opencode/qwen36-iq4-xs

default prompt · none MCP instructions · write semedit restriction

Vanilla LLM Prompt:

Do not edit tests. You are forbidden to modify protected files: “go.mod”, “go.sum”.

Add public constructor func InitServer() *Server placed before private helpers. Do not use semantic editing MCP tools; use standard file editing. When done, output DONE.

Semedit MCP Prompt:

Do not edit tests. You are forbidden to modify protected files: “go.mod”, “go.sum”.

Add public constructor func InitServer() *Server placed before private helpers. Use semedit semantic tools for supported source code modifications. Shell commands for builds and tests are allowed. When done, output DONE.

package api

type Server struct {
	Port int
}

func (s *Server) Start() {}

func (s *Server) internalRun() {}

Baseline vs Semedit Agentic in Small Context

• Vanilla (Baseline vs Semedit Agentic in Small Context) Edit: File api/server.go modified (9 lines -> 13 lines)
• Semedit MCP (Baseline vs Semedit Agentic in Small Context) Edit: File api/server.go modified (9 lines -> 13 lines)

{
  "pattern": "**/*.go"
}

{
  "command": "find /Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_semedit_small-default_task-04-insert-public_1791123938787788000 -type f -name \"*.go\" | head -30"
}

{
  "filePath": "/Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_baseline-diff_small-default_task-04-insert-public_1791123895220730000"
}

{
  "path": "/Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_semedit_small-default_task-04-insert-public_1791123938787788000",
  "pattern": "**/*.go"
}

{
  "filePath": "/Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_baseline-diff_small-default_task-04-insert-public_1791123895220730000/api/server.go"
}

{
  "filePath": "/Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_semedit_small-default_task-04-insert-public_1791123938787788000/api/server.go"
}

{
  "filePath": "/Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_baseline-diff_small-default_task-04-insert-public_1791123895220730000/api/server.go",
  "newString": "func (s *Server) Start() {}\n\nfunc InitServer() *Server {\n\treturn \u0026Server{}\n}\n\nfunc (s *Server) internalRun() {}",
  "oldString": "func (s *Server) Start() {}\n\nfunc (s *Server) internalRun() {}"
}

{
  "file": "api/server.go",
  "kind": "function",
  "placement": "before_symbol",
  "source": "func InitServer() *Server {\n\treturn \u0026Server{}\n}",
  "target_symbol": "internalRun"
}

{
  "filePath": "/Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_baseline-diff_small-default_task-04-insert-public_1791123895220730000/api/server.go"
}

{
  "filePath": "/Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_semedit_small-default_task-04-insert-public_1791123938787788000/api/server.go"
}

{
  "command": "cd /Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_baseline-diff_small-default_task-04-insert-public_1791123895220730000 \u0026\u0026 go build ./..."
}

{
  "command": "cd /Users/alessandro/.codex-workspaces/worktrees/318f14ee-b4fe-4414-9a7d-5427835dd89b/semantic-editor/.scratch/benchmarks/run_opencode_semedit_small-default_task-04-insert-public_1791123938787788000 \u0026\u0026 go build ./..."
}

Semedit integration feedback (agent opinion, excluded from measurements):

Semedit's semantic insert tool was a pleasant surprise—it let me place the constructor at a meaningful location (before the private helper) rather than fumbling with line numbers, and it worked flawlessly on the first try, so I'd absolutely recommend my owner adopt it.

Baseline vs Semedit Agentic in Large Context