As regular readers are aware, I do a lot of informal lit review. So I was especially interested in checking out the various AI based “deep research” tools and seeing how they compare.

I did a side-by-side comparison, using the same prompt, of Perplexity Deep Research, Gemini Deep Research, ChatGPT-4o Deep Research, Elicit, and PaperQA.

General Impressions

The Deep Research bots are useful, but I wouldn’t consider them a replacement for my own lit reviews.

None of them produce really big lit reviews — they’re all typically capped at 40 sources. If I’m doing a “heavy” or exhaustive lit review, I’ll go a lot farther. (And, in fact, for the particular project I used as an example here, I intend to do a manual version to catch things that didn’t make it into the AI reports.)

[...]

---

Outline:

(00:45) General Impressions

(02:37) Prompt

(03:33) Perplexity Deep Research

(03:40) Completeness: C

(04:02) Relevance: C

(04:13) Credibility: B

(04:28) Overall Grade: C+

(04:33) Gemini Advanced Deep Research

(04:40) Completeness: B-

(05:03) Relevance: A

(05:14) Credibility: B-

(05:33) Overall Grade: B

(05:38) ChatGPT-4o Deep Research

(05:46) Completeness: A

(06:07) Relevance: A

(06:19) Credibility: A

(06:29) Overall Grade: A

(06:33) Elicit Research Report

(06:40) Completeness: B+

(07:02) Relevance: A

(07:14) Credibility: A+

(07:34) Overall Grade: A-

(07:39) PaperQA

(07:50) Completeness: A-

(08:12) Relevance: A

(08:24) Credibility: A

(08:34) Overall Grade: A

(08:39) Final Thoughts: Creativity

---

First published:

Source:

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.