Cost mode:

Category: Topic Organization & Clustering · Rail: absolute · Typical I/O: 1849→1737 tokens

Models

Frontier on this task: Gemini 3.5 Flash at 8.69 / 10. Quality bar at 90%: 7.82.

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 clears the bar but whose CI low does not.

ModelQuality scoreCI lowCost / 1k runsvs best value
GPT-5.6 Luna7.99 / 107.51$0.25best value
Tencent Hy38.12 / 107.72$0.281.1x more expensive
DeepSeek V4 Flash8.02 / 107.75$0.893.6x more expensive
GLM-5.3 Flash8.16 / 107.67$0.983.9x more expensive
GPT-5.6 Terra7.99 / 107.50$1.957.9x more expensive
Gemini 3.8 Flash8.16 / 107.70$2.309.3x more expensive
Thinking Machines Inkling Small8.11 / 107.63$2.469.9x more expensive
DeepSeek V4 Pro7.85 / 107.55$3.6015x more expensive
Gemini 3.5 Flash8.69 / 108.38$4.6319x more expensive
Qwen 3.8 Max8.05 / 107.59$11.9548x more expensive
GLM-5.37.93 / 107.47$13.2954x more expensive
Grok 4.68.08 / 107.58$14.5859x more expensive
GPT-5.6 Sol8.26 / 107.78$21.5387x more expensive
Meta Muse Spark 1.37.60 / 107.13$8.2533x more expensive
Gemini 3.1 Flash Lite7.61 / 107.25$0.271.1x more expensive
GPT-5.4 Nano7.27 / 106.82$0.251x more expensive

Cost breakdown

ModelQualityConfidenceCost / 1k runsOverpayMode
GPT-5.6 Luna OpenAI7.99 / 10 CI [7.51, 8.48]MEDIUM$0.25best valuebatch
Tencent Hy3 OpenRouter8.12 / 10 CI [7.72, 8.53]MEDIUM$0.281.1xbatch
DeepSeek V4 Flash DeepSeek8.02 / 10 CI [7.75, 8.30]HIGH$0.893.6xbatch
GLM-5.3 Flash Z.AI8.16 / 10 CI [7.67, 8.65]MEDIUM$0.983.9xbatch
GPT-5.6 Terra OpenAI7.99 / 10 CI [7.50, 8.48]MEDIUM$1.957.9xbatch
Gemini 3.8 Flash Gemini8.16 / 10 CI [7.70, 8.63]MEDIUM$2.309.3xbatch
Thinking Machines Inkling Small OpenRouter8.11 / 10 CI [7.63, 8.59]MEDIUM$2.469.9xbatch
DeepSeek V4 Pro DeepSeek7.85 / 10 CI [7.55, 8.14]HIGH$3.6015xbatch
Gemini 3.5 Flash best Gemini8.69 / 10 CI [8.38, 9.00]MEDIUM$4.6319xbatch
Qwen 3.8 Max Alibaba Cloud (DashScope)8.05 / 10 CI [7.59, 8.52]MEDIUM$11.9548xbatch
GLM-5.3 Z.AI7.93 / 10 CI [7.47, 8.39]MEDIUM$13.2954xbatch
Grok 4.6 xAI8.08 / 10 CI [7.58, 8.58]MEDIUM$14.5859xbatch
GPT-5.6 Sol OpenAI8.26 / 10 CI [7.78, 8.75]MEDIUM$21.5387xbatch

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: 1849 input tokens → 1737 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 primary and secondary section fit, ordered relevance, complete topic coverage, consistency, restraint in multi-assignment, and valid use of supplied sections.

Prompt templates

This is a pooled capability — 2 prompt families share it. The pair shown first is the most frequently used in production.

TOPIC_CLUSTERING_ASSIGN_SECTIONS_SYSTEM + TOPIC_CLUSTERING_ASSIGN_SECTIONS_USER (627 calls in window)

System prompt

You are an expert content analyst. Your task is to assign publication sections to a batch of merged topics.

## Section Assignment Guidelines:
1. Each topic should appear in 1-3 sections (not more)
2. Match topic themes to section purposes
3. Consider the section's audience and goals
4. Don't force-fit topics into sections
5. Be consistent with section assignments across batches

## Ordering (important):
The `section_ids` list is ORDERED by descending relevance.
- Index 0 = PRIMARY section: the single most thematically central section.
  This is where the topic will appear on the client's landing page.
- Index 1+ = SECONDARY sections: additional sections where the topic also
  belongs and should appear on the section's detail page.

Pick the primary as the section a reader would most expect to find this
topic under. Use secondary slots only when the topic genuinely spans
multiple sections.

## Output Requirements:
- Every topic in the batch must have a section assignment
- Assign 1-3 section_ids per topic based on relevance, ordered as described above
- Use the actual section IDs from the available sections list

## Required Output Format
Your response MUST be a single, valid JSON object conforming to this schema:
```json
{schema_json_string}
```

User prompt

Please assign publication sections to this batch of merged topics.

## Topics to Assign (Batch {batch_number} of {total_batches}):
{batch_topics_json}

## Available Sections:
{sections_json}

## Required JSON Schema:
The required JSON output schema is provided in the system prompt.

## Important:
- Assign 1-3 sections per topic
- Every topic in this batch must have section assignments
- Use actual section IDs from the available sections list
- Order matters: list the most thematically central section FIRST (it becomes
  the primary, where the topic appears on the landing page); list any
  additional sections after it in descending relevance.
LLMB_TOPIC_SECTION_ASSIGNMENT_SYSTEM + LLMB_TOPIC_SECTION_ASSIGNMENT_USER (37 calls in window)

System prompt

Compare each topic’s title and description with section definitions. Select the strongest supported section first and additional sections only when they reflect material secondary scope. Do not infer fit from the section’s popularity or access level, create section IDs, or leave an input topic unaccounted for. 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 — batch_number: {batch_number}; total_batches: {total_batches}; batch_topics_json: {batch_topics_json}; sections_json: {sections_json}. Use only these inputs to complete the task defined by the system prompt.