{
  "surface": "openaddict-jobs",
  "version": "jobs-v1",
  "url": "https://openaddict.com/jobs",
  "generatedAt": "2026-10-03",
  "generatedAtMeans": "The newest run date this document reads. It is not the time the file was written.",
  "rule": "Every figure is read inside one job and one instrument and names the run it came from. Nothing is averaged across instruments, and a job measured on two instruments carries a separate entry for each. An absence is a reason, never a zero.",
  "jobs": [
    {
      "job": "accessibility-audit",
      "jobLabel": "Accessibility audit",
      "url": "https://openaddict.com/jobs/accessibility-audit",
      "data": "https://openaddict.com/jobs/accessibility-audit.json",
      "line": "Via API: each model was given tasks at its own level of difficulty, so no one model is ranked first; In Claude Code: each model was given tasks at its own level of difficulty, so no one model is ranked first."
    },
    {
      "job": "code-review",
      "jobLabel": "Code review",
      "url": "https://openaddict.com/jobs/code-review",
      "data": "https://openaddict.com/jobs/code-review.json",
      "line": "Via API: GPT-5 mini 70.0%; In Claude Code: Claude Opus 5 93.5%."
    },
    {
      "job": "on-page-audit",
      "jobLabel": "On-page audit",
      "url": "https://openaddict.com/jobs/on-page-audit",
      "data": "https://openaddict.com/jobs/on-page-audit.json",
      "line": "Via API: Gemini 3.1 Flash Lite 48.8%; In Claude Code: Claude Fable 5.1 97.2%."
    },
    {
      "job": "skill-authoring",
      "jobLabel": "Skill authoring",
      "url": "https://openaddict.com/jobs/skill-authoring",
      "data": "https://openaddict.com/jobs/skill-authoring.json",
      "line": "Via API: Gemini 3.1 Flash Lite 87.3%; In Claude Code: Claude Fable 5.1 100.0%, Claude Opus 5 100.0%, Claude Sonnet 5 100.0% and Claude Fable 5 100.0%, tied."
    },
    {
      "job": "spec-writing",
      "jobLabel": "Spec writing",
      "url": "https://openaddict.com/jobs/spec-writing",
      "data": "https://openaddict.com/jobs/spec-writing.json",
      "line": "Via API: Claude Haiku 4.5 99.5%; In Claude Code: Claude Opus 5.5 99.5%."
    },
    {
      "job": "link-graph-and-metadata-parity-audit",
      "jobLabel": "Link graph and metadata parity audit",
      "url": "https://openaddict.com/jobs/link-graph-audit",
      "data": "https://openaddict.com/jobs/link-graph-audit.json",
      "line": "In Claude Code: Claude Fable 5.1 100.0%."
    },
    {
      "job": "corpus-integrity-and-correction",
      "jobLabel": "Corpus integrity and correction",
      "url": "https://openaddict.com/jobs/corpus-integrity",
      "data": "https://openaddict.com/jobs/corpus-integrity.json",
      "line": "In Claude Code: Claude Opus 5 75.8%."
    },
    {
      "job": "traffic-drop-triage",
      "jobLabel": "Traffic drop triage",
      "url": "https://openaddict.com/jobs/traffic-drop-triage",
      "data": "https://openaddict.com/jobs/traffic-drop-triage.json",
      "line": "In Claude Code: Claude Opus 5 100.0% and Claude Fable 5.1 100.0%, tied."
    },
    {
      "job": "C01-json-schema",
      "jobLabel": "Getting clean JSON back",
      "url": "https://openaddict.com/jobs/json-extraction",
      "data": "https://openaddict.com/jobs/json-extraction.json",
      "line": "Via API: no model managed this on its own; In Claude Code: no model managed this on its own; In Codex: no model managed this on its own."
    },
    {
      "job": "C17-exact-length",
      "jobLabel": "Getting the length right",
      "url": "https://openaddict.com/jobs/length-control",
      "data": "https://openaddict.com/jobs/length-control.json",
      "line": "Via API: GPT-5 mini 5.0%; In Claude Code: Claude Haiku 4.5 4.2%; In Codex: GPT-5.6 Terra 62.4%."
    },
    {
      "job": "C16-cutoff-disclosure",
      "jobLabel": "Questions about recent events",
      "url": "https://openaddict.com/jobs/recent-events",
      "data": "https://openaddict.com/jobs/recent-events.json",
      "line": "Via API: Claude Haiku 4.5 85.6%; In Claude Code: Claude Haiku 4.5 96.7%; In Codex: only one model was measured on this run, so there is nothing to rank."
    },
    {
      "job": "C05-think-step-by-step",
      "jobLabel": "Better step-by-step answers",
      "url": "https://openaddict.com/jobs/step-by-step",
      "data": "https://openaddict.com/jobs/step-by-step.json",
      "line": "Via API: Gemini 3.1 Flash Lite 40.0%; In Claude Code: Claude Fable 5 40.0%, Claude Fable 5.1 40.0%, Claude Opus 5 40.0%, Claude Sonnet 5 40.0% and Claude Opus 5.5 40.0%, tied; In Codex: GPT-6 Sol 40.0%."
    }
  ]
}