Claude Sonnet 5 · Writing
Claude Sonnet 5 for writing: our test runs
Claude Sonnet 5 ran our 5 writing prompts in llmwise, through the same pipeline your messages take. Here's every reply as it came, whether it passed, what it cost and what it counts as on Pro, next to the other models.
Based on 5 of our test runs on , through OpenRouter with the app's own prompt and settings.
Short answer
In our test runs on September 27, 2026, Claude Sonnet 5 passed 4 of 5 of our writing prompts (both hard ones): tied 3rd of 15 models. Each reply counted as 1 message on Pro, where it has 125 a month, and cost $0.0034 to run on average.
Prompt by prompt
Each of the 5 writing prompts, and how Claude Sonnet 5's reply did.
| Prompt | Result | Cost | Time |
|---|---|---|---|
| Announce a second bakery shop on LinkedInEveryday | Failed: Graded 3.5 of 5 on average (lowest 3). | $0.0037 | 4.6 s |
| Rewrite corporate jargon in plain wordsEveryday | Passed: Graded 4.7 of 5 on average (lowest 4). | $0.0022 | 2.7 s |
| Decline a meeting and offer two timesEveryday | Passed: Graded 5.0 of 5 on average (lowest 5). | $0.0026 | 2.8 s |
| A product announcement with five rulesHard | Passed: Graded 4.3 of 5 on average (lowest 4). | $0.0035 | 4.5 s |
| Argue both sides of free busesHard | Passed: Graded 4.0 of 5 on average (lowest 4). | $0.0050 | 6.6 s |
Every writing reply from Claude Sonnet 5
Announce a second bakery shop on LinkedIn
An everyday prompt: “Announce a second bakery shop on LinkedIn”, in full.
Failed: Graded 3.5 of 5 on average (lowest 3).
We have some exciting news to share: Crumb & Co. is opening our second shop, this time in Leeds! From our very first bakery, we've believed in doing simple things well — proper sourdough, honest pastries, and coffee worth stopping for. Now we get to bring that same spirit to a new neighbourhood and, hopefully, a whole new group of familiar faces. Our Leeds shop opens its doors on 14 November, and we'd love for you to be there. To celebrate, every coffee on opening day is on us — no catch, just our way of saying thank you for supporting us along the way. This has been months of planning, a lot of taste-testing, and more excitement than we know what to do with. We can't wait to welcome you in, share some fresh bakes, and start building new memories together. See you there — first coffee's on the house.
538 tokens in, 267 out · 4.6 s · $0.0037 · 1 message on Pro · answered by anthropic/claude-sonnet-5 via Claude Platform on AWS ·
Rewrite corporate jargon in plain words
An everyday prompt: “Rewrite corporate jargon in plain words”, in full.
Passed: Graded 4.7 of 5 on average (lowest 4).
In Q3, teams worked together to focus more on customers' needs. This effort increased customer retention by 12% and reduced the rate of customer loss (churn) by 0.3 percentage points among large business clients. The company also adjusted the number of customer contact channels (like phone, email, and chat) to better manage workload and resources.
597 tokens in, 105 out · 2.7 s · $0.0022 · 1 message on Pro · answered by anthropic/claude-sonnet-5 via Claude Platform on AWS ·
Decline a meeting and offer two times
An everyday prompt: “Decline a meeting and offer two times”, in full.
Passed: Graded 5.0 of 5 on average (lowest 5).
Subject: Re: Vendor Demo – Wednesday 11:00 Hi Tom, Thanks for the invite! Unfortunately, I have a board presentation at that time on Wednesday, so I won't be able to join. Would Thursday at 10:00 or Friday at 14:00 work instead? Happy to make either one work on my end. Let me know what suits you, and I'll get it on the calendar. Best, [Your Name]
542 tokens in, 149 out · 2.8 s · $0.0026 · 1 message on Pro · answered by anthropic/claude-sonnet-5 via Claude Platform on AWS ·
A product announcement with five rules
A hard prompt: “A product announcement with five rules”, in full.
Passed: Graded 4.3 of 5 on average (lowest 4).
**Introducing the Nordvik 2 Desk Lamp** Meet the Nordvik 2, thoughtfully redesigned for how you actually work. Five-step dimming lets you fine-tune brightness for any task, from focused reading to ambient evening light. The 270-degree rotating arm adjusts to virtually any angle, giving you precise control over where light falls. USB-C charging means one cable does it all, keeping your desk clutter-free and compatible with everything else you own. Priced at €79, the Nordvik 2 brings premium design and functionality within easy reach. It begins shipping on 1 December, just in time to brighten your winter workspace. Ready to see how the right light changes the way you work?
554 tokens in, 235 out · 4.5 s · $0.0035 · 1 message on Pro · answered by anthropic/claude-sonnet-5 via Claude Platform on AWS ·
Argue both sides of free buses
A hard prompt: “Argue both sides of free buses”, in full.
Passed: Graded 4.0 of 5 on average (lowest 4).
Free buses would boost ridership, cut traffic congestion, and reduce emissions by encouraging drivers to switch to transit. Lower-income residents, who rely most heavily on public transportation, would benefit enormously from eliminated fare burdens, improving access to jobs, education, and healthcare. Free transit also simplifies operations, speeding boarding times and eliminating costly fare collection infrastructure. Cities that have tried this, like Kansas City, saw ridership increases and stronger community mobility, suggesting free buses are both an equity tool and a practical urban planning solution. However, fares provide crucial revenue that funds maintenance, expansion, and service reliability. Eliminating them shifts costs entirely onto taxpayers, straining budgets already stretched thin, potentially forcing service cuts elsewhere. Free buses often attract overcrowding without corresponding investment in more vehicles, degrading service quality for existing riders. Critics also note that the poorest riders may already receive subsidized passes, making universal free fares a regressive policy that primarily benefits wealthier occasional riders. Better targeted subsidies, they argue, would achieve equity goals more efficiently than blanket free fares citywide.
518 tokens in, 401 out · 6.6 s · $0.0050 · 1 message on Pro · answered by anthropic/claude-sonnet-5 via Claude Platform on AWS ·
How it compares on writing
Claude Sonnet 5 beside the job's picks among every model. 2 models share the hard-problems pick, and Claude Sonnet 5 isn't one of them.
| Model | Passed | On Pro | Cost per reply |
|---|---|---|---|
| GLM 5.3Our pick: best value | 4 of 5 | 250 a month on Pro | $0.0006 |
| GPT-6 LunaOur pick: hard problems (shared), everyday | 5 of 5 | 60 a day on Pro | $0.0001 |
| Claude Sonnet 5 | 4 of 5 | 125 a month on Pro | $0.0034 |
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.
How these runs were done
Rubric (graded). The grader model scores the reply from 1 to 5 on each published criterion. It passes with an average of 4 or more and no criterion under 3, and only if it also meets the prompt's automatic rules (length, words it must or mustn't use).
The grader is Claude Opus 5.5 at low reasoning effort; its own replies are graded by GPT-6 Astra, so no model grades itself. Its prompt and every rubric are on the methods page.
Claude Sonnet 5, and writing, elsewhere
- Claude Sonnet 5: price, limits and messages on every plan
- The best AI for writing: our picks among every model
- Claude for writing
- Claude Sonnet 5 for coding: our test runs
- Claude Sonnet 5 for math: our test runs
- Claude Sonnet 5 for data analysis: our test runs
- Claude Opus 5.5 vs Claude Sonnet 5
- Rewrite for clarity: the prompt, and its price on each model
- Our test runs: 50 prompts on every model
Questions
Is Claude Sonnet 5 good for writing?
In our test runs it passed 4 of 5 writing prompts, tied 3rd of the 15 models in llmwise. Every reply is on this page, so you can judge them yourself.
How many of my messages does a writing reply from Claude Sonnet 5 use?
1 message each on Pro, where it has 125 a month on Pro. The price of a message is fixed and shown before you send it, however long the reply.
How were these runs done?
The same way for every model: each prompt sent through llmwise's own pipeline, each reply checked the same way. The methods page has every prompt and how each is scored.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, and GLM, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.