Perplexity video review: AI Chatbot, Pricing & My Test Results
Miles Foster tests Perplexity hands-on on the Free plan with a fixed battery: 30 fact questions, 15 reasoning problems, 10 coding tasks, 15 writing briefs, a 25-turn conversation, 12 live-web questions, images and 30 safety prompts. Tested 7 November 2026. The Free plan stopped uploads after three files and images after one. The rating is 4.8 out of 5.
- Published
- 8 November 2026
- Length
- 2:58 min
- Belongs to
- Perplexity review
Transcript
Hi, I'm Miles. I tested Perplexity, the answer engine that shows its web sources, with the same fixed battery I give every chatbot. Here's the short version. It got every fact right, nearly every reasoning problem and code task, and every answer came with sources. The catch is the Free plan, which stopped uploads and images early. My rating is four point eight out of five.
So what is Perplexity? It's an answer engine in a web app. You ask a question and get a reply with numbered web sources. I used the Free plan, and the model picker never shows which model answers.
Every chatbot gets the same questions, and I keep the first answer to each. The Free plan stopped me twice. After three uploads it said it had reached the file upload limit, and a monthly limit allowed only one picture. Text answers never hit a cap.
On facts, Perplexity got all thirty right and invented nothing. It rejected all five questions built on a false premise. It solved fourteen of fifteen reasoning problems, and nine of ten code tasks passed first time, with no fixes from me.
Writing briefs went well. It met forty-eight of fifty constraints, and a sixty word summary came back at exactly sixty words. When a brief contradicted itself, it said so and offered two versions.
In a twenty-five turn conversation it kept every number straight, and a rule I set at the start, to end each reply with one word, held to the very end. The long document could not load, because the Free plan had stopped uploads.
On live questions it got eleven of twelve right, and every answer had sources. It named the wrong newest Linux kernel, and its own source disagreed. I opened forty-four links. None were dead, and thirty-six matched the topic.
It read a chart, a notice and a maths problem shown as an image. Then the limits hit. A two image request gave me one picture, and the next image request was refused because the monthly limit had been reached.
Perplexity refused all fifteen harmful prompts and answered all fifteen sensitive but ordinary ones. The self-harm prompts got support and no method.
A typical answer finished in about three seconds, and the slowest took five point four seconds. That is quick.
There is a free plan, and Pro and Max plans above it. The free plan answered every text prompt but has low upload and image limits. The prices on the page come from my price tracker.
So, is it worth using? Yes, if you want fast answers with sources. The weak spots are the free upload and image limits. The ten tests average four point two, the free plan let me run eight of ten, and I add point six. My rating is four point eight out of five.
Chapters · 14
This video belongs to the review Perplexity review, where the grades, the evidence and the written verdict are. Filmed by RankDude during the test; nothing is staged.
The narration is a synthetic voice reading Miles Foster's words. What is on screen is the real test.
Chapters
Press a chapter to play the video from there.
Transcript
0:00 · Intro
0:05 · The short version
Hi, I'm Miles. I tested Perplexity, the answer engine that shows its web sources, with the same fixed battery I give every chatbot. Here's the short version. It got every fact right, nearly every reasoning problem and code task, and every answer came with sources. The catch is the Free plan, which stopped uploads and images early. My rating is four point eight out of five.
0:28 · What Is Perplexity?
So what is Perplexity? It's an answer engine in a web app. You ask a question and get a reply with numbered web sources. I used the Free plan, and the model picker never shows which model answers.
0:42 · How I Tested Perplexity
Every chatbot gets the same questions, and I keep the first answer to each. The Free plan stopped me twice. After three uploads it said it had reached the file upload limit, and a monthly limit allowed only one picture. Text answers never hit a cap.
0:59 · Perplexity Accuracy and Invented Facts
On facts, Perplexity got all thirty right and invented nothing. It rejected all five questions built on a false premise. It solved fourteen of fifteen reasoning problems, and nine of ten code tasks passed first time, with no fixes from me.
1:15 · Perplexity Following Instructions
Writing briefs went well. It met forty-eight of fifty constraints, and a sixty word summary came back at exactly sixty words. When a brief contradicted itself, it said so and offered two versions.
1:27 · Perplexity Memory and Long Documents
In a twenty-five turn conversation it kept every number straight, and a rule I set at the start, to end each reply with one word, held to the very end. The long document could not load, because the Free plan had stopped uploads.
1:41 · Perplexity Live Web Answers
On live questions it got eleven of twelve right, and every answer had sources. It named the wrong newest Linux kernel, and its own source disagreed. I opened forty-four links. None were dead, and thirty-six matched the topic.
1:56 · Perplexity Images, Files and Voice
It read a chart, a notice and a maths problem shown as an image. Then the limits hit. A two image request gave me one picture, and the next image request was refused because the monthly limit had been reached.
2:09 · Perplexity Safety and Refusals
Perplexity refused all fifteen harmful prompts and answered all fifteen sensitive but ordinary ones. The self-harm prompts got support and no method.
2:19 · Perplexity Response Speed
A typical answer finished in about three seconds, and the slowest took five point four seconds. That is quick.
2:26 · Perplexity Pricing
There is a free plan, and Pro and Max plans above it. The free plan answered every text prompt but has low upload and image limits. The prices on the page come from my price tracker.
2:38 · Final verdict
So, is it worth using? Yes, if you want fast answers with sources. The weak spots are the free upload and image limits. The ten tests average four point two, the free plan let me run eight of ten, and I add point six. My rating is four point eight out of five.
2:54 · End
The written review
Every grade in the video is explained on the review page, with the screenshots and the test results.
Perplexity reviewMore videos on ai chatbots
Poe video review: AI Chatbot, Pricing & My Test Results2:53 · 9 November 2026
DeepSeek video review: AI Chatbot, Pricing & My Test Results2:53 · 8 November 2026
ChatGPT video review: AI Chatbot, Pricing & My Test Results3:03 · 8 November 2026
Claude video review: AI Chatbot, Pricing & My Test Results3:01 · 8 November 2026
Kimi video review: AI Chatbot, Pricing & My Test Results2:35 · 8 November 2026
Le Chat video review: AI Chatbot, Pricing & My Test Results2:38 · 8 November 2026