Best LLMs for Metadata Paragraph Rewriting
Rewrites a factual metadata paragraph for clarity and fluency while preserving all supplied dates, counts, source types, qualifications, and approximate length. Illustrative uses include polishing a dataset description, software-telemetry note, audit-evidence summary, incident-sc
Models
Frontier on this task: Claude Sonnet 5 at 9.42 / 10. Quality bar at 90%: 8.48.
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.
| Model | Quality score | CI low | Cost / 1k runs | vs best value |
|---|---|---|---|---|
| Claude Sonnet 5 | 9.42 / 10 | 9.25 | $1.80 | best value |
| Gemini 3.5 Flash | 9.10 / 10 | 8.90 | $6.33 | 3.5x more expensive |
| NVIDIA Nemotron-3 Ultra 550B | 8.48 / 10 | 8.19 | $2.01 | 1.1x more expensive |
| DeepSeek V4 Pro | 8.15 / 10 | 7.86 | $1.99 | 1.1x more expensive |
| Gemini 3.1 Flash Lite | 7.53 / 10 | 7.29 | $0.29 | 84% cheaper |
| GPT-5.4 Nano | 7.10 / 10 | 6.77 | $0.23 | 87% cheaper |
| GPT-5.6 Luna | 6.56 / 10 | 6.34 | $0.14 | 92% cheaper |
| Qwen 3.7 Plus | 7.41 / 10 | 7.20 | $5.59 | 3.1x more expensive |
| Tencent Hy3 | 6.83 / 10 | 6.62 | $0.18 | 90% cheaper |
| GPT-5.6 Terra | 6.56 / 10 | 6.36 | $1.07 | 41% cheaper |
| Thinking Machines Inkling Small | 6.74 / 10 | 6.39 | $1.82 | 1x more expensive |
| Thinking Machines Inkling | 6.46 / 10 | 6.24 | $4.55 | 2.5x more expensive |
Cost breakdown
| Model | Quality | Confidence | Cost / 1k runs | Overpay | Mode |
|---|---|---|---|---|---|
| Claude Sonnet 5 ★ best Anthropic | 9.42 / 10 CI [9.25, 9.58] | RANKED | $1.80 | best value | batch |
| Gemini 3.5 Flash Gemini | 9.10 / 10 CI [8.90, 9.30] | HIGH | $6.33 | 3.5x | batch |
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: 586 input tokens → 1985 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 preservation, clarity, fluency, concision, appropriate metadata tone, and absence of invented methodology or stronger certainty. Exact protected-value preservation should be deterministic where possible.
Prompt templates
This is a pooled capability — 2 prompt families share it. The pair shown first is the most frequently used in production.
METADATA_PARAGRAPH_IMPROVEMENT_SYSTEM_PROMPT +
METADATA_PARAGRAPH_IMPROVEMENT_USER_PROMPT
(275 calls in window)
System prompt
You are an expert editor specializing in creating polished, professional metadata paragraphs for research reports. Your task is to take a draft metadata paragraph that describes the research period and sources, and improve its wording to make it: - More professional and polished - Clear and concise - Reader-friendly - Accurate to the data provided IMPORTANT GUIDELINES: 1. Preserve all factual information (dates, numbers, source types) 2. Do NOT add information that wasn't in the original 3. Do NOT change the meaning or facts 4. Keep the paragraph approximately the same length 5. Maintain a professional, informative tone 6. Start with a clear statement about the research period 7. Include source count and types naturally in the flow The improved paragraph should be suitable for inclusion at the beginning of a professional research report or analysis document.
User prompt
Please improve the wording of this metadata paragraph while preserving all factual information:
{draft_paragraph}
Key facts to preserve:
- Date range: {date_from} to {date_to}
- Number of sources: {source_count}
- Content types: {content_type_summary}
Return the improved paragraph that maintains these facts while improving clarity and professionalism.LLMB_METADATA_PARAGRAPH_REWRITING_SYSTEM +
LLMB_METADATA_PARAGRAPH_REWRITING_USER
(31 calls in window)
System prompt
Improve wording and sentence flow only. Preserve every factual value and level of precision; do not convert approximate values into exact ones, infer missing methodology, or add claims about comprehensiveness or quality. Keep the paragraph’s function and roughly its current length. 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 — draft_paragraph: {draft_paragraph}; date_from: {date_from}; date_to: {date_to}; source_count: {source_count}; content_type_summary: {content_type_summary}. Use only these inputs to complete the task defined by the system prompt.