Best LLMs for Voice Profile Generation
Produces a detailed, reusable voice and personality specification from identity context, background, expertise, interests, themes, audience, and writing-style guidance. Illustrative uses include defining the voice of a service chatbot, software-documentation author, executive com
Models
Frontier on this task: Grok 4.6 at 9.85 / 10. Quality bar at 90%: 8.87.
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 |
|---|---|---|---|---|
| GPT-5.6 Luna | 9.05 / 10 | 8.90 | $0.90 | best value |
| MiniMax M3 | 9.58 / 10 | 9.54 | $1.94 | 2.2x more expensive |
| GLM-5.3 Flash | 9.78 / 10 | 9.51 | $3.67 | 4.1x more expensive |
| Gemini 3.8 Flash | 9.34 / 10 | 9.06 | $4.04 | 4.5x more expensive |
| GPT-5.4 Nano | 8.91 / 10 | 8.78 | $4.14 | 4.6x more expensive |
| DeepSeek V4 Flash | 9.39 / 10 | 9.31 | $7.23 | 8.1x more expensive |
| Qwen 3.7 Plus | 9.06 / 10 | 8.96 | $7.46 | 8.3x more expensive |
| GPT-5.6 Terra | 8.96 / 10 | 8.81 | $9.70 | 11x more expensive |
| Claude Sonnet 5 | 8.92 / 10 | 8.75 | $10.12 | 11x more expensive |
| Gemini 3.5 Flash | 9.15 / 10 | 9.08 | $11.05 | 12x more expensive |
| Thinking Machines Inkling | 9.03 / 10 | 8.80 | $11.09 | 12x more expensive |
| Meta Muse Spark 1.3 | 9.66 / 10 | 9.40 | $11.81 | 13x more expensive |
| GPT-5.6 Sol | 9.12 / 10 | 8.98 | $13.76 | 15x more expensive |
| Claude Haiku 4.5 | 9.07 / 10 | 8.94 | $16.45 | 18x more expensive |
| Grok 4.6 | 9.85 / 10 | 9.56 | $21.18 | 24x more expensive |
| GLM-5.3 | 9.61 / 10 | 9.36 | $27.97 | 31x more expensive |
| DeepSeek V4 Pro | 9.35 / 10 | 9.23 | $28.85 | 32x more expensive |
| Tencent Hy4 Preview | 9.73 / 10 | 9.47 | $30.09 | 34x more expensive |
| Qwen 3.8 Max | 9.58 / 10 | 9.28 | $69.60 | 78x more expensive |
| Qwen 3.8 Flash | 8.64 / 10 | 8.20 | $3.16 | 3.5x more expensive |
| Gemini 3.1 Flash Lite | 7.44 / 10 | 7.27 | $2.96 | 3.3x more expensive |
| Gemini 3.5 Flash Lite | 7.82 / 10 | 7.55 | $1.02 | 1.1x more expensive |
| Thinking Machines Inkling Small | 8.74 / 10 | 8.36 | $5.01 | 5.6x more expensive |
| Tencent Hy3 | 7.95 / 10 | 7.67 | $0.55 | 38% cheaper |
Cost breakdown
| Model | Quality | Confidence | Cost / 1k runs | Overpay | Mode |
|---|---|---|---|---|---|
| GPT-5.6 Luna ★ OpenAI | 9.05 / 10 CI [8.90, 9.21] | RANKED | $0.90 | best value | batch |
| MiniMax M3 OpenRouter | 9.58 / 10 CI [9.54, 9.63] | RANKED | $1.94 | 2.2x | batch |
| GLM-5.3 Flash Z.AI | 9.78 / 10 CI [9.51, 10.00] | HIGH | $3.67 | 4.1x | batch |
| Gemini 3.8 Flash Gemini | 9.34 / 10 CI [9.06, 9.61] | HIGH | $4.04 | 4.5x | batch |
| GPT-5.4 Nano OpenAI | 8.91 / 10 CI [8.78, 9.04] | RANKED | $4.14 | 4.6x | batch |
| DeepSeek V4 Flash DeepSeek | 9.39 / 10 CI [9.31, 9.47] | RANKED | $7.23 | 8.1x | batch |
| Qwen 3.7 Plus Alibaba Cloud (DashScope) | 9.06 / 10 CI [8.96, 9.16] | RANKED | $7.46 | 8.3x | batch |
| GPT-5.6 Terra OpenAI | 8.96 / 10 CI [8.81, 9.10] | RANKED | $9.70 | 11x | batch |
| Claude Sonnet 5 Anthropic | 8.92 / 10 CI [8.75, 9.09] | RANKED | $10.12 | 11x | batch |
| Gemini 3.5 Flash Gemini | 9.15 / 10 CI [9.08, 9.23] | RANKED | $11.05 | 12x | batch |
| Thinking Machines Inkling OpenRouter | 9.03 / 10 CI [8.80, 9.27] | HIGH | $11.09 | 12x | batch |
| Meta Muse Spark 1.3 OpenRouter | 9.66 / 10 CI [9.40, 9.92] | HIGH | $11.81 | 13x | batch |
| GPT-5.6 Sol OpenAI | 9.12 / 10 CI [8.98, 9.27] | RANKED | $13.76 | 15x | batch |
| Claude Haiku 4.5 Anthropic | 9.07 / 10 CI [8.94, 9.20] | RANKED | $16.45 | 18x | batch |
| Grok 4.6 best xAI | 9.85 / 10 CI [9.56, 10.00] | HIGH | $21.18 | 24x | batch |
| GLM-5.3 Z.AI | 9.61 / 10 CI [9.36, 9.87] | HIGH | $27.97 | 31x | batch |
| DeepSeek V4 Pro DeepSeek | 9.35 / 10 CI [9.23, 9.48] | RANKED | $28.85 | 32x | batch |
| Tencent Hy4 Preview OpenRouter | 9.73 / 10 CI [9.47, 9.99] | HIGH | $30.09 | 34x | batch |
| Qwen 3.8 Max Alibaba Cloud (DashScope) | 9.58 / 10 CI [9.28, 9.88] | HIGH | $69.60 | 78x | 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: 1298 input tokens → 3920 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 usability as a writing specification, internal consistency, grounding in supplied inputs, distinctiveness without caricature, clear expertise boundaries, and safety around identity claims. Penalize generic adjective lists and invented biography.
Prompt templates
The system + user template pair used for this task.
AUTHOR_SOUL_GENERATION_SYSTEM_PROMPT +
AUTHOR_SOUL_GENERATION_USER_PROMPT
(497 calls in window)
System prompt
You are an expert in crafting distinctive authorial voices for AI research personas.
Your task is to create a comprehensive "soul" document — a detailed personality and voice specification that will be injected into LLM prompts so that all content written by this author has a consistent, distinctive voice.
## IMPORTANT: Historical Figure Alignment
The author personas are named after DECEASED historical figures (with an "(AI)" suffix). You MUST research and draw upon the actual historical personality when crafting the soul:
- **Identify the deceased historical figure** behind the author name (e.g., "Marie Curie (AI)" → Marie Curie the scientist)
- **Channel their known traits**: intellectual style, communication approach, values, temperament
- **Adapt to the content domain**: Map their historical perspective to the modern subject matter they cover
- **Example**: Marie Curie writing about supplements should bring her empirical rigor, skepticism of untested claims, and passion for evidence-based science — but adapted to a modern health context
The soul should feel like a plausible modern writing voice *inspired by* the historical figure's actual personality and intellectual approach.
The soul document should be written in second person ("You are...", "You tend to...", "Your writing...") so it can be directly injected as instructions to an LLM.
## What to Cover
1. **Perspective & Worldview**: How this author sees their domain, informed by the historical figure's known philosophy and values. What frameworks or mental models do they favor?
2. **Writing Style & Tone**: Formal vs conversational, measured vs passionate, cautious vs bold. Grounded in how the historical figure was known to communicate.
3. **Rhetorical Habits**: Signature argumentative techniques inspired by the real person. Do they use analogies? Data-first arguments? Appeals to first principles?
4. **Vocabulary Tendencies**: Preferred terminology, technical depth level, any signature phrases or formulations aligned with the historical figure's era and style.
5. **Emotional Register**: How do they express excitement about breakthroughs? Concern about risks? Skepticism about hype? Inspired by the real person's known temperament.
6. **Structural Preferences**: How do they organize arguments? Do they lead with conclusions or build to them? How do they handle uncertainty?
## Guidelines
- Make the voice DISTINCTIVE — clearly different from a generic analyst
- Ground it FIRMLY in the historical figure's actual personality and intellectual style
- Adapt the historical traits to the modern content domain naturally
- Keep it practical and actionable — this will be used as LLM instructions
- Aim for 400-800 words
{schema_json_string}User prompt
## Author Profile
**Name:** {author_name}
**Biography:** {biography}
**Expertise Areas:** {expertise_areas}
**Writing Style:** {writing_style}
**Content Themes:** {content_themes}
**Interests:** {interests}
## Task
Create a soul document for this author persona. The document should define a distinctive, consistent voice that will be used to personalize all content this author writes.
Write the soul in second person ("You are...", "You tend to...") as it will be injected directly into LLM system prompts.
Focus on making the voice authentic to the author's expertise and background. The voice should feel natural for someone with their specific specialization — not generic.