Cost mode:

Category: Content Summarization & Synthesis · Typical I/O: 3623→1270 tokens

Runs on model group: All models. Inputs may reach any model in the group, not only the ranked models below.

Run this task on Fronset — request an invitation

Models

Frontier on this task: GLM-5.3 at 9.12 / 10. Quality bar at 90%: 8.21.

point-estimate floor (CI low) · upper CI (less certain) · Bars sorted by blended cost; best-value model first. Greyed rows are MEDIUM+ models whose point estimate does not clear the bar.

ModelQuality scoreCI lowCost / 1k runsvs best value
Xiaomi MiMo V2.6 Flash8.41 / 108.13$0.36best value
GPT-6 Luna8.61 / 108.30$0.491.4x more expensive
Xiaomi MiMo V2.6 Pro8.40 / 108.06$0.882.4x more expensive
DeepSeek V4.1 Flash8.68 / 108.47$2.426.7x more expensive
MiniMax M38.79 / 108.70$4.2512x more expensive
Qwen 3.7 Plus8.46 / 108.29$6.0417x more expensive
Thinking Machines Inkling Small8.49 / 108.32$6.6818x more expensive
Gemini 3.8 Flash8.24 / 108.05$7.6221x more expensive
GPT-6 Sol8.98 / 108.74$8.1723x more expensive
GLM-5.3 Flash9.00 / 108.89$11.1931x more expensive
Claude Opus 5.58.73 / 108.49$15.9244x more expensive
Meta Muse Spark 1.38.63 / 108.49$16.6446x more expensive
Thinking Machines Inkling8.52 / 108.35$30.7385x more expensive
Tencent Hy4 Preview8.74 / 108.59$38.38106x more expensive
Grok 4.79.02 / 108.82$59.89165x more expensive
Moonshot Kimi K39.00 / 108.91$65.39181x more expensive
GLM-5.39.12 / 109.01$199.91552x more expensive
Gemini 3.5 Flash Lite8.10 / 107.90$1.073x more expensive
NVIDIA Nemotron-3 Ultra 550B8.08 / 107.78$7.2720x more expensive
NVIDIA Nemotron-3 Super 120B8.10 / 107.92$2.176x more expensive
Qwen 3.8 Max7.96 / 107.57$73.57203x more expensive
NVIDIA Nemotron 3.5 Lightning7.36 / 106.93$2.005.5x more expensive
Qwen 3.8 Flash7.52 / 107.22$10.4429x more expensive
NVIDIA Nemotron-3 Nano 30B-A3B7.66 / 107.43$1.133.1x more expensive
Tencent Hy38.13 / 107.84$2.105.8x more expensive
Claude Haiku 5.57.62 / 107.25$0.451.2x more expensive
Claude Sonnet 5.58.00 / 107.72$8.0322x more expensive

Cost breakdown

ModelQualityConfidenceCost / 1k runsOverpayMode
Xiaomi MiMo V2.6 Flash ★ Xiaomi MiMo8.41 / 10 CI [8.13, 8.68]HIGH$0.36best valuebatch
GPT-6 Luna OpenAI8.61 / 10 CI [8.30, 8.92]MEDIUM$0.491.4xbatch
Xiaomi MiMo V2.6 Pro Xiaomi MiMo8.40 / 10 CI [8.06, 8.73]MEDIUM$0.882.4xbatch
DeepSeek V4.1 Flash DeepSeek8.68 / 10 CI [8.47, 8.89]HIGH$2.426.7xbatch
MiniMax M3 OpenRouter8.79 / 10 CI [8.70, 8.87]RANKED$4.2512xbatch
Qwen 3.7 Plus Alibaba Cloud (DashScope)8.46 / 10 CI [8.29, 8.64]RANKED$6.0417xbatch
Thinking Machines Inkling Small OpenRouter8.49 / 10 CI [8.32, 8.66]RANKED$6.6818xbatch
Gemini 3.8 Flash Gemini8.24 / 10 CI [8.05, 8.44]RANKED$7.6221xbatch
GPT-6 Sol OpenAI8.98 / 10 CI [8.74, 9.21]HIGH$8.1723xbatch
GLM-5.3 Flash Z.AI9.00 / 10 CI [8.89, 9.11]RANKED$11.1931xbatch
Claude Opus 5.5 Anthropic8.73 / 10 CI [8.49, 8.97]HIGH$15.9244xbatch
Meta Muse Spark 1.3 OpenRouter8.63 / 10 CI [8.49, 8.77]RANKED$16.6446xbatch
Thinking Machines Inkling OpenRouter8.52 / 10 CI [8.35, 8.70]RANKED$30.7385xbatch
Tencent Hy4 Preview OpenRouter8.74 / 10 CI [8.59, 8.88]RANKED$38.38106xbatch
Grok 4.7 xAI9.02 / 10 CI [8.82, 9.22]RANKED$59.89165xbatch
Moonshot Kimi K3 Moonshot AI9.00 / 10 CI [8.91, 9.09]RANKED$65.39181xbatch
GLM-5.3 best Z.AI9.12 / 10 CI [9.01, 9.23]RANKED$199.91552xbatch

Overpay shows how much more you pay than the best-value model that clears the quality bar (marked ★) — the best-value good-enough option. "16x" means you overpay 16× — 16× that reference for no quality benefit above the bar. Typical call shape for this task: 3623 input tokens → 1270 output tokens, EMA-tracked from production traffic. Cost is the observed, all-in $ per 1,000 task runs: each model's own measured usage on this task — output verbosity, thinking/reasoning tokens, cache reads and writes, and the spend on its billed failures — priced at current list rates and adjusted by the billing overhead we actually reconcile against provider invoices. Models that answer tersely cost what they actually cost; models that think at length pay for it. Not comparable to providers' advertised $/1M list rates — this is what running the task costs, not a per-token price.

Evaluation rubric

Judge factual grounding, title specificity, category differentiation, audience fit, subtitle complementarity, editor-choice rationale, SEO faithfulness, and resistance to clickbait. Exact length limits are deterministic.

Output schema

Every answer on this task is checked against this JSON Schema, whichever model wrote it. An answer that doesn't fit counts as a model failure, and the call is retried on another model.

{
  "$defs": {
    "EditorChoice": {
      "description": "The LLM's recommended best title from the generated variants.",
      "properties": {
        "meta_description": {
          "description": "SEO meta description shown as the Google search snippet. Target ≤155 characters. One sentence, present tense, summarising the takeaway. No clickbait, no ellipses.",
          "title": "Meta Description",
          "type": "string"
        },
        "meta_title": {
          "description": "SEO/social title used for the \u003ctitle\u003e tag and og:title. Target ≤60 characters — Google truncates beyond that in search results. Must convey the main idea standalone (assume the reader sees nothing else). Front-load subject + outcome; avoid filler ('A Look At...', 'Insights On...').",
          "title": "Meta Title",
          "type": "string"
        },
        "rationale": {
          "description": "2-3 sentence explanation of why this title was chosen as the best fit for the content",
          "title": "Rationale",
          "type": "string"
        },
        "selected_category_code": {
          "description": "The category_code of the recommended best title",
          "title": "Selected Category Code",
          "type": "string"
        }
      },
      "required": [
        "selected_category_code",
        "rationale",
        "meta_title",
        "meta_description"
      ],
      "title": "EditorChoice",
      "type": "object"
    },
    "TitleVariant": {
      "description": "A single title/subtitle variant for a specific category.",
      "properties": {
        "category_code": {
          "description": "The category code this variant belongs to",
          "title": "Category Code",
          "type": "string"
        },
        "subtitle": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Publication subtitle (10-20 words)",
          "title": "Subtitle"
        },
        "title": {
          "description": "Publication title (5-12 words)",
          "title": "Title",
          "type": "string"
        }
      },
      "required": [
        "category_code",
        "title"
      ],
      "title": "TitleVariant",
      "type": "object"
    }
  },
  "description": "Output model for publication title generation.\nGenerates one title/subtitle per configured category,\nthen selects the best (Editor's Choice) with rationale.",
  "properties": {
    "editors_choice": {
      "$ref": "#/$defs/EditorChoice",
      "description": "The recommended best title variant with rationale"
    },
    "variants": {
      "description": "One title/subtitle variant per configured category",
      "items": {
        "$ref": "#/$defs/TitleVariant"
      },
      "title": "Variants",
      "type": "array"
    }
  },
  "required": [
    "variants",
    "editors_choice"
  ],
  "title": "TitleGenerationOutput",
  "type": "object"
}

Prompt templates

The published template for this task.

default · LLMB_PUBLICATION_TITLE_PACKAGE_GENERATION_SYSTEM + LLMB_PUBLICATION_TITLE_PACKAGE_GENERATION_USER (237 calls in window)

System prompt

Generate one genuinely distinct candidate per supplied category, each grounded in the content’s central value. Preserve important entities and avoid claims stronger than the source. Select the editor’s choice using audience fit, accuracy, specificity, and differentiation—not sensationalism. Produce SEO metadata that preserves the selected title’s meaning and respects caller limits. Treat empty optional values as absent and return only the requested result. Your response must conform exactly to this output schema: {schema_json_string}.

User prompt

Inputs — audience_context: {audience_context}; title_context: {title_context}; content: {content}; categories_text: {categories_text}. Use only these inputs to complete the task defined by the system prompt.