Anthropic has just released Claude Sonnet 5 for all users, and I wanted to test what it was good at. But the game has changed now. Sonnet 5 doesn't feel dramatically different from Gemini or ChatGPT if you ask it ordinary chatbot questions. Instead, the difference should show up when you stop asking for answers and start asking for completed work.

Anthropic says Sonnet 5 is built for "multi-step software engineering work," sustained coding, tool use, debugging, and "messy technical contexts." It also says it can make plans, use browsers and terminals, and run more autonomously than smaller, cheaper models previously could.

I'm not using Sonnet 5 for coding, but that doesn't mean I can't take advantage of its new abilities — just like you can. So I stopped asking Claude for answers and started asking it to finish jobs, beginning with planning a trip to Bath, UK, for my family: my wife, me, and two teens.

A trip to Bath

When I tested it, Claude Sonnet 5 defaulted to its Medium level of effort, so that's what I used. Here's the first prompt I tried:

"I want to test whether you can act more like an agent than a chatbot.

My task is: Plan a weekend trip to Bath for two adults and two teenagers, including travel, lunch, one activity, estimated costs, and what still needs booking.

Don't just give me advice. First, make a brief plan. Then identify which parts of the task you can complete yourself right now, which parts require tools or information you don't have, and which parts need human judgment.

Then complete as much of the task as possible without stopping after the first obvious answer.

At the end, give me:

What you completed

What still needs human action

Any assumptions you made

A short checklist I can use to verify the result

The next best step"

What I really liked was that, as Claude tackled this task, it gave me the option to be notified when it had finished. In reality, it only took a few seconds to come back with a plan, which included travel options, an itinerary, and a suggestion for lunch and something to do: a trip to The Roman Baths.

To my delight Claude gave me an interactive map showing where all the places it recommended were. It also gave me a useful list of what it had completed, what required human action, the assumptions it had made, a verification checklist, and a "next best step" action point. It felt ready to keep working with me as more details came in, rather than treating its first answer as final.

In fact, when I gave it more details, such as which day I was going to go, it gave me a visual weather report for the day. That was a really nice touch.

Claude vs ChatGPT

I also tried this prompt with ChatGPT-5.5 Medium and got a similar result. It acted as an agent, just like Claude did, and notified me when it had finished its tasks. It just didn't look as nice. There was no map, or any visual elements at all, and it felt more like I had been given a finished report than the start of a two-way conversation where it asked me for more details.

Both chatbots recommended lunch and a trip to The Roman Baths. Interestingly, ChatGPT assumed I’d get the train, while Claude assumed I’d drive. They also recommended different places to eat, but the core information they both provided was solid.

What was most impressive was that both models could adapt when I reframed the inputs. For example, when I gave them the ages of the kids, student status, a different mode of transport, or changed the day of the trip, both models could cope. Both also identified that since the oldest was a university student, he could get free entry to The Roman Baths.

This part of the test was probably the most meaningful, as it felt much more "multi-step" than simply providing one answer.

Overall, I’d give this test to Claude. You can clearly see that Sonnet 5 is set up for agentic actions. Neither Claude nor ChatGPT could actually do any of the booking for me at the moment, so we're still a long way from true personal-assistant-level autonomy. But for this kind of task, Claude currently has the edge.

A different domain

I wanted to test the models in a different domain that would let Claude show me it had genuinely improved, and that the Bath trip result was not just a fluke of the travel-planning use case. So I asked them both to:

"Build me a simple household budget tracker as a spreadsheet or small tool."

Both models thought for a while about this task, and churned through various options before opting to make a spreadsheet. ChatGPT produced a spreadsheet with a bar chart that tracked how much I’d spent on various household expenses against a budget. Claude, however, went for something simpler: dispensing with a budget, it just tracked actual expenses and created a pie chart showing where my money was going.

Claude’s initial approach was simpler, and easier to understand. Both models provided a .xlsx file, but only Claude provided a button to upload it straight to Google Drive so I could open it in Sheets.

I told ChatGPT, "I wanted the graph to be a pie chart," and it responded: "Absolutely — I’ll update the spreadsheet itself so the dashboard uses a pie chart for spending by category, rather than the current graph style."

It ran into a few problems because it was trying to show both the budget and actual values in the same pie chart, but eventually it worked out that it could show only one and produced a new spreadsheet that did exactly what I asked for.

I then asked Claude to change its spreadsheet to provide a budget section too, and to change the graph into a bar chart. Again, it showed me its workings and added a budget section and bar charts perfectly.

I can’t really separate the two AI models on this task. Both proved they can handle multi-step tasks well, and both were happy to revise the result when I changed the brief.

That, really, is the point. The most interesting AI tests now are not "which chatbot gives the best answer?" They are "which assistant keeps working until the job is actually done?"

On that front, Claude Sonnet 5 feels extremely capable. ChatGPT was close behind, and in some ways just as effective, but Claude felt more naturally organized around the idea of completing work rather than simply responding to prompts. It asked fewer invisible questions, presented its output more helpfully, and made the whole process feel more like collaborating with an assistant than interrogating a chatbot.

For now, neither model is ready to fully take over the job. I still had to check the details, make the decisions, and do the actual booking or uploading myself. But the direction of travel is obvious. The AI war is no longer just about who has the smartest chatbot. It’s about who can build the assistant that gets you closest to a finished task.

ChatGPT's new finance feature lets the AI chatbot take a look at any bank or similar accounts you care to open up for inspection. I was initially hesitant to try it out, but the tool only looks at the details of how you spend your money, and can't actually carry out transactions, so I agreed to let it analyze some of my accounts and offer its insights.

Finances is currently only available in the U.S. to Plus and Pro users on web, iOS, and Android. Setting everything up is as easy as using any other ChatGPT plug-in. You just select Finances in ChatGPT and then click Get Started then Connect with Plaid.

Finances uses Plaid to link to the accounts; you simply sign in and agree to let Plaid share the information. The service synchronized recent transactions and basically became an interactive, conversational database of my information. It's not that the AI can do things it couldn't before, but now you don't have to manually enter any finance details you want to ask it about.

ChatGPT looks at the receipts

At its suggestion, I asked ChatGPT, "How much did I spend eating out this year?" ChatGPT soon had a breakdown of my how much I had spent at various restaurants, including delivery, and broke down some of the patterns. It pointed out that it had gone up recently, which makes sense as the weather has became pleasant enough to walk into town more often to eat. It also identified a few spikes I could tell were around birthdays and family celebrations.

Next I asked, "What subscriptions am I paying for?"

That turned into one of the most practical moments of the experiment. ChatGPT gathered recurring charges across streaming services, software, and other monthly payments into one clear summary instead of leaving me hunting through statements. It also suggested reviewing whether every subscription still deserved a place in my budget.

"These subscriptions appear consistently each month, making them reliable recurring expenses.", it told me.

Financial chatter

Seeking a more detailed analysis, I asked ChatGPT, "What's changed in my spending this month?"

Instead of overwhelming me with every purchase, ChatGPT focused on the transactions that genuinely stood out. It noted a few large purchases at new locations, and asked if they were something I wanted more information on. I told it those were gifts, and the AI incorporated that fact into its response as not a new regular event but one that explained why overall spending had climbed this month.

"Those gift purchases are unusual compared with your recent history but they account for much of the increase, so your everyday spending has remained relatively consistent despite the higher overall total. Looking beyond one unusual month provides a more accurate picture of your longer term financial habits."

Using ChatGPT this way felt almost like the inverse of most financial software. Most budgeting apps expect you to learn their system first. ChatGPT let me ask questions however they occurred to me and then translated months of transactions into answers that were easy to understand.

That does not mean it replaces dedicated budgeting tools, and it certainly cannot make smarter financial decisions on your behalf. You still have to decide whether to cancel subscriptions, spend less on eating out, or save more each month. But I can see how it might make it easier for people who hesitate to look at their finances if they feel uncomfortable around spreadsheets. It didn't feel like math homework the way it often does.

Of course, it still relies on some trust in both OpenAI and Plaid, but as long as it's purely viewing and not actually touching the accounts, this could be a really useful, practical feature for ChatGPT users.