Bakeoff

Model bakeoff 2026-08-27T17:51:14.968Z

2 profiles · Aug 27, 2026, 5:51 PM UTC

Profile

glm-5-3-flash-b

ready · QA pass
arm baselineexemplar source scrubbedregen 0
glm-5-3-flash-b ↗$0.0164
8,990 in11,802 out$0.0164 cost419.0s workflow wall371.3s LLM call time
StepProvider:modelEffortPrompt variantTokensCostStep wall time
planopenrouter:z-ai/glm-5.3-flashlowdefault1,229 / 2,108$0.0012242.7s
art_directionopenrouter:z-ai/glm-5.3-flashlowdefault
theme_emitopenrouter:z-ai/glm-5.3-flashlowdefault2,901 / 8,085$0.0022119.2s
hero_continuationopenrouter:z-ai/glm-5.3-flashlowdefault
page_generateopenrouter:z-ai/glm-5.3-flashlowdefault
honesty_repairopenrouter:z-ai/glm-5.3-flashlowdefault
honesty_judgeopenrouter:anthropic/claude-haiku-4.5default4,860 / 1,609$0.01299.4s
visual_qaopenrouter:anthropic/claude-haiku-4.5default
visual_repairopenrouter:z-ai/glm-5.3-flashlowdefault
restyleopenrouter:z-ai/glm-5.3-flashlowdefault
Submitted profile JSON
{
  "name": "glm-5-3-flash-b",
  "steps": {
    "theme_emit": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    },
    "page_generate": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    },
    "plan": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    },
    "restyle": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    },
    "honesty_judge": {
      "provider": "openrouter",
      "model": "anthropic/claude-haiku-4.5"
    },
    "honesty_repair": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    }
  }
}
Resolved run profile
[
  {
    "step": "plan",
    "role": "plan",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 420000
  },
  {
    "step": "art_direction",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 1600,
    "temperature": 0.4,
    "timeoutMs": 90000
  },
  {
    "step": "theme_emit",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 420000
  },
  {
    "step": "hero_continuation",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 16000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "page_generate",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 420000
  },
  {
    "step": "honesty_repair",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 420000
  },
  {
    "step": "honesty_judge",
    "role": "claims_judge",
    "provider": "openrouter",
    "model": "anthropic/claude-haiku-4.5",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 4096,
    "temperature": 0,
    "timeoutMs": 60000
  },
  {
    "step": "visual_qa",
    "role": "claims_judge",
    "provider": "openrouter",
    "model": "anthropic/claude-haiku-4.5",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 1200,
    "temperature": 0,
    "timeoutMs": 20000
  },
  {
    "step": "visual_repair",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0,
    "timeoutMs": 420000
  },
  {
    "step": "restyle",
    "role": "plan",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 420000
  }
]

result 2843c614-0451-442c-8342-2d5e27b2c6f5 job 27a85130-59fe-4e8b-a76e-1e08921af527 site bo-site-2843c614-0451-442c-8342-2d5e27b2c6f5

Profile

glm-5-3-flash-c

ready · QA pass
arm baselineexemplar source creativeregen 0
glm-5-3-flash-c ↗$0.0175
9,039 in11,157 out$0.0175 cost266.8s workflow wall222.2s LLM call time
StepProvider:modelEffortPrompt variantTokensCostStep wall time
planopenrouter:z-ai/glm-5.3-flashlowdefault1,229 / 1,187$0.000444.5s
art_directionopenrouter:z-ai/glm-5.3-flashlowdefault
theme_emitopenrouter:z-ai/glm-5.3-flashlowdefault2,831 / 8,487$0.0047170.2s
hero_continuationopenrouter:z-ai/glm-5.3-flashlowdefault
page_generateopenrouter:z-ai/glm-5.3-flashlowdefault
honesty_repairopenrouter:z-ai/glm-5.3-flashlowdefault
honesty_judgeopenrouter:anthropic/claude-haiku-4.5default4,979 / 1,483$0.01247.5s
visual_qaopenrouter:anthropic/claude-haiku-4.5default
visual_repairopenrouter:z-ai/glm-5.3-flashlowdefault
restyleopenrouter:z-ai/glm-5.3-flashlowdefault
Submitted profile JSON
{
  "name": "glm-5-3-flash-c",
  "steps": {
    "theme_emit": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    },
    "page_generate": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    },
    "plan": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    },
    "restyle": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    },
    "honesty_judge": {
      "provider": "openrouter",
      "model": "anthropic/claude-haiku-4.5"
    },
    "honesty_repair": {
      "provider": "openrouter",
      "model": "z-ai/glm-5.3-flash",
      "effort": "low",
      "timeoutMs": 420000
    }
  }
}
Resolved run profile
[
  {
    "step": "plan",
    "role": "plan",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 420000
  },
  {
    "step": "art_direction",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 1600,
    "temperature": 0.4,
    "timeoutMs": 90000
  },
  {
    "step": "theme_emit",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 420000
  },
  {
    "step": "hero_continuation",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 16000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "page_generate",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 420000
  },
  {
    "step": "honesty_repair",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 420000
  },
  {
    "step": "honesty_judge",
    "role": "claims_judge",
    "provider": "openrouter",
    "model": "anthropic/claude-haiku-4.5",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 4096,
    "temperature": 0,
    "timeoutMs": 60000
  },
  {
    "step": "visual_qa",
    "role": "claims_judge",
    "provider": "openrouter",
    "model": "anthropic/claude-haiku-4.5",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 1200,
    "temperature": 0,
    "timeoutMs": 20000
  },
  {
    "step": "visual_repair",
    "role": "generation",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0,
    "timeoutMs": 420000
  },
  {
    "step": "restyle",
    "role": "plan",
    "provider": "openrouter",
    "model": "z-ai/glm-5.3-flash",
    "effort": "low",
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 420000
  }
]

result cf77b5ab-a355-4c85-beb2-7cadde5cf1d7 job 2445d397-ba19-47da-88cc-cdeadf12a69d site bo-site-cf77b5ab-a355-4c85-beb2-7cadde5cf1d7

Workflow provenance

Git SHA
unknown-local-build
Captured
Aug 27, 2026, 5:51 PM UTC
  1. startValidate business data; mark the job and bakeoff result running.
  2. pipeline / planBuild the full SEO page plan through the selected plan profile.
  3. pipeline / generateGenerate the homepage theme and scoped pages, repairing or falling back safely.
  4. pipeline / visual QAWhen enabled, render desktop/mobile, run the vision critic, and verify up to two surgical homepage repairs.
  5. pipeline / assembleAssemble raw HTML/CSS/JS with shared SEO, navigation, business facts, and legal pages.
  6. pipeline / auditRun deterministic QA plus the independent honesty judge.
  7. pipeline / writeWrite the validated mutable draft and its source/provenance artifacts to tenant R2.
  8. finishFinalize generation job, site metadata, and page rows in D1.
  9. domainsBest-effort domain candidate discovery used by the real claim path.
  10. bakeoff-finalizeBakeoff-only: publish an immutable preview snapshot and roll up LLM usage.