Claude 3.7 Sonnet for creative writing
Claude 3.7 Sonnet is ranked #4 on LLMDex's llm for creative writing ranking out of 5 models we track for this use case. Below, the specific reasons it slots where it does, and when you should reach for an alternative.
Updated
At a glance
- Rank
- #4 of 5
- Context
- 200K tokens
- Output / 1M
- $15.00 / 1M tokens
- Released
- Feb 2025
Why Claude 3.7 Sonnet fits this task
Three things about Claude 3.7 Sonnet that map directly onto what this task rewards: Mature, widely-tested. Beyond the task-specific fit, Claude 3.7 Sonnet also brings first claude with extended thinking and excellent writing and coding quality, both of which compound when the workload broadens.
The criteria this task rewards
LLMDex ranks best llm for creative writing on 5 criteria , these are the axes the ranking uses, in priority order:
- Voice consistency across long passages
- Avoidance of LLM-isms ("shimmering," "tapestry," "in conclusion")
- Narrative coherence and chapter-to-chapter memory
- Style transfer, can it write in your voice with a few examples?
- Refusal patterns on mature content (varies wildly by provider)
How Claude 3.7 Sonnet scores on each axis
Where Claude 3.7 Sonnet costs you: superseded by 4.x for most new workloads. For most teams this is acceptable on this workload, the value of the strengths above outweighs the cost. For cost-bound workloads or teams with strict latency budgets, run an eval against the next two ranked models on real data before committing.
Strengths that pay off here
- First Claude with extended thinking
- Excellent writing and coding quality
- Mature, widely-tested
Tracked weaknesses
- Superseded by 4.x for most new workloads
When to pick something else
If you can pay slightly more or accept slightly different tradeoffs, GPT-5.5 from OpenAI ranks one position higher and tends to win on the hardest cases. OpenAI's mid-cycle GPT-5 refresh, improved reasoning, tool use, and multimodal grounding over the 2025 launch.
Run Claude 3.7 Sonnet now
Skip setup. Deploy via a hosted provider in under a minute.
Other models for creative writing
- Claude Opus 4.7 for creative writing
Anthropic's mid-2026 flagship, ahead on SWE-bench, agent reliability, and writing quality.
Read guide - Claude Sonnet 4.6 for creative writing
Anthropic's mid-tier 4.6 release, the workhorse model behind most production Anthropic deployments.
Read guide - GPT-5.5 for creative writing
OpenAI's mid-cycle GPT-5 refresh, improved reasoning, tool use, and multimodal grounding over the 2025 launch.
Read guide - Gemini 3 Pro for creative writing
Google's late-2025 flagship, set new benchmarks on long-context, vision, and reasoning at competitive pricing.
Read guide
Claude 3.7 Sonnet for other use cases
Direct comparisons
Frequently asked
Is Claude 3.7 Sonnet good for creative writing?
Claude 3.7 Sonnet is ranked #4 on LLMDex's creative writing list. The first Claude with an extended-thinking mode, ushered the reasoning-model paradigm into Anthropic's lineup.How much does Claude 3.7 Sonnet cost for creative writing?
Claude 3.7 Sonnet costs $3.00 / 1M tokens for input tokens and $15.00 / 1M tokens for output tokens. For creative writing workloads, output costs typically dominate; budget on the higher number.What's a cheaper alternative to Claude 3.7 Sonnet for creative writing?
The next ranked model on this task is Gemini 3 Pro. Compare both before committing.When should I NOT use Claude 3.7 Sonnet for creative writing?
Tracked weakness: Superseded by 4.x for most new workloads. If that constraint is binding for your workload, the next-ranked model on this task is the safer pick.
Intelligence, distilled weekly.
One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.