Every tool starts at zero and earns points for what it does and what it costs. Here is exactly what earns them.
The short version
These tools do different jobs, so each kind has its own checklist: literature search tools on 6 things, paper readers on 6 things and systematic review platforms on 6 things. Each checklist is worth 100 points, and a tool is only ranked against its own kind.
The final score is those points out of 10. A tool with 84 points scores 8.4.
Everything comes from the tool's own website. We don't take payment for points.
Literature search tools
Finding papersReading and analysing papersSystematic reviewsPricingCiting and writingAccess, teams and privacy
What earns points
1. Finding papers
20 of 100 pointsCan it find the papers you need? Search across published research, answers to a research question that cite their sources, maps of connected papers and alerts when something new comes out.
Searches a database of papersup to 3
Answers a research question from the literatureup to 2.5
Map of connected papersup to 1.5
Alerts for new papersup to 1.5
Shows if later papers support or dispute a paperup to 1.5
Each section adds up to 10, then counts for 20 of the 100.
2. Reading and analysing papers
25 of 100 pointsOnce you have the papers, can it help you understand them? Asking questions of a paper, summaries, pulling data out of many papers at once, and answers you can check against the text.
Ask questions of a paperup to 2
Pulls data from many papers into a tableup to 2
Summarises papersup to 1.5
Answers show the passage they came fromup to 1.5
Reads tables and figuresup to 1.5
Writes a literature review for youup to 1.5
Each section adds up to 10, then counts for 25 of the 100.
3. Systematic reviews
10 of 100 pointsCan it run a systematic review: screening with include and exclude decisions, AI help with screening, removing duplicates, a PRISMA diagram and risk of bias?
Screening with include and exclude decisionsup to 3
AI help with screeningup to 2
Removes duplicate referencesup to 2
PRISMA flow diagramup to 1.5
Risk of bias assessmentup to 1.5
Each section adds up to 10, then counts for 10 of the 100.
4. Pricing
20 of 100 pointsWhat the cheapest paid plan costs, at the academic rate where the vendor publishes one. A free tool earns the most points.
Tools charge in different ways, so there is one price table for each. Only the table that matches how a tool charges counts, so a fee per use or a yearly price is never compared with a monthly plan.
Monthly price, cheapest paid plan (academic rate if offered)up to 10
| Free | +10 |
| Up to $10 | +9 |
| Up to $15 | +8 |
| Up to $20 | +7 |
| Up to $30 | +5.5 |
| Up to $50 | +4 |
| Up to $80 | +2.5 |
| Over $80 | +1 |
Yearly price, sold by the year onlyup to 10
| Free | +10 |
| Up to $120 | +9 |
| Up to $180 | +8 |
| Up to $240 | +7 |
| Up to $360 | +5.5 |
| Up to $600 | +4 |
| Up to $960 | +2.5 |
| Over $960 | +1 |
Each section adds up to 10, then counts for 20 of the 100.
5. Citing and writing
15 of 100 pointsDoes it fit how you write? Your reference manager, the export formats you need, help with writing, and add-ins for your browser and word processor.
Works with Zotero, Mendeley, EndNote and othersup to 3.5
| None | 0 |
| 1 reference manager | +2 |
| 2 reference managers | +3 |
| 3 reference managers or more | +3.5 |
Export formatsup to 2.5
| None | 0 |
| 1 format | +1 |
| 2 formats | +2 |
| 3 formats or more | +2.5 |
Helps you write and adds citationsup to 1.5
Browser extensionup to 1.25
Word or Google Docs add-inup to 1.25
Each section adds up to 10, then counts for 15 of the 100.
6. Access, teams and privacy
10 of 100 pointsCan your university or library license it, can you share projects with your team, and does it keep your uploads out of its AI training?
University or library licenceup to 3
Shared projects with your teamup to 2
Works in languages other than Englishup to 1
Does not train AI on your dataup to 1
| Yes | +1 |
| Only if you opt out | +0.5 |
| No | 0 |
Each section adds up to 10, then counts for 10 of the 100.
A real example: Elicit
Here is how Elicit got its 7.8.
| Section | Points |
|---|
| Finding papers | 14 of 20 |
| Reading and analysing papers | 25 of 25 |
| Systematic reviews | 8.5 of 10 |
| Pricing | 14 of 20 |
| Citing and writing | 8.6 of 15 |
| Access, teams and privacy | 7.5 of 10 |
| Total | 77.6 of 100 = 7.8 out of 10 |
See every fact behind Elicit's score.
Paper readers
Finding papersReading and analysing papersSystematic reviewsPricingCiting and writingAccess, teams and privacy
What earns points
1. Finding papers
20 of 100 pointsCan it find the papers you need? Search across published research, answers to a research question that cite their sources, maps of connected papers and alerts when something new comes out.
Searches a database of papersup to 3
Answers a research question from the literatureup to 2.5
Map of connected papersup to 1.5
Alerts for new papersup to 1.5
Shows if later papers support or dispute a paperup to 1.5
Each section adds up to 10, then counts for 20 of the 100.
2. Reading and analysing papers
25 of 100 pointsOnce you have the papers, can it help you understand them? Asking questions of a paper, summaries, pulling data out of many papers at once, and answers you can check against the text.
Ask questions of a paperup to 2
Pulls data from many papers into a tableup to 2
Summarises papersup to 1.5
Answers show the passage they came fromup to 1.5
Reads tables and figuresup to 1.5
Writes a literature review for youup to 1.5
Each section adds up to 10, then counts for 25 of the 100.
3. Systematic reviews
10 of 100 pointsCan it run a systematic review: screening with include and exclude decisions, AI help with screening, removing duplicates, a PRISMA diagram and risk of bias?
Screening with include and exclude decisionsup to 3
AI help with screeningup to 2
Removes duplicate referencesup to 2
PRISMA flow diagramup to 1.5
Risk of bias assessmentup to 1.5
Each section adds up to 10, then counts for 10 of the 100.
4. Pricing
20 of 100 pointsWhat the cheapest paid plan costs, at the academic rate where the vendor publishes one. A free tool earns the most points.
Tools charge in different ways, so there is one price table for each. Only the table that matches how a tool charges counts, so a fee per use or a yearly price is never compared with a monthly plan.
Monthly price, cheapest paid plan (academic rate if offered)up to 10
| Free | +10 |
| Up to $10 | +9 |
| Up to $15 | +8 |
| Up to $20 | +7 |
| Up to $30 | +5.5 |
| Up to $50 | +4 |
| Up to $80 | +2.5 |
| Over $80 | +1 |
Yearly price, sold by the year onlyup to 10
| Free | +10 |
| Up to $120 | +9 |
| Up to $180 | +8 |
| Up to $240 | +7 |
| Up to $360 | +5.5 |
| Up to $600 | +4 |
| Up to $960 | +2.5 |
| Over $960 | +1 |
Each section adds up to 10, then counts for 20 of the 100.
5. Citing and writing
15 of 100 pointsDoes it fit how you write? Your reference manager, the export formats you need, help with writing, and add-ins for your browser and word processor.
Works with Zotero, Mendeley, EndNote and othersup to 3.5
| None | 0 |
| 1 reference manager | +2 |
| 2 reference managers | +3 |
| 3 reference managers or more | +3.5 |
Export formatsup to 2.5
| None | 0 |
| 1 format | +1 |
| 2 formats | +2 |
| 3 formats or more | +2.5 |
Helps you write and adds citationsup to 1.5
Browser extensionup to 1.25
Word or Google Docs add-inup to 1.25
Each section adds up to 10, then counts for 15 of the 100.
6. Access, teams and privacy
10 of 100 pointsCan your university or library license it, can you share projects with your team, and does it keep your uploads out of its AI training?
University or library licenceup to 3
Shared projects with your teamup to 2
Works in languages other than Englishup to 1
Does not train AI on your dataup to 1
| Yes | +1 |
| Only if you opt out | +0.5 |
| No | 0 |
Each section adds up to 10, then counts for 10 of the 100.
A real example: Anara
Here is how Anara got its 7.3.
| Section | Points |
|---|
| Finding papers | 11 of 20 |
| Reading and analysing papers | 25 of 25 |
| Systematic reviews | 0 of 10 |
| Pricing | 16 of 20 |
| Citing and writing | 14.3 of 15 |
| Access, teams and privacy | 7 of 10 |
| Total | 73.3 of 100 = 7.3 out of 10 |
See every fact behind Anara's score.
Systematic review platforms
Running the reviewExtraction and analysisTeams, access and privacyPricingFinding papersCiting and exports
What earns points
1. Running the review
40 of 100 pointsCan it run the review itself? Screening with include and exclude decisions, AI help with screening, removing duplicate references, a PRISMA flow diagram and risk of bias assessment. This is what a review team buys it for, so it carries the most points.
Screening with include and exclude decisionsup to 3
AI help with screeningup to 2
Removes duplicate referencesup to 2
PRISMA flow diagramup to 1.5
Risk of bias assessmentup to 1.5
Each section adds up to 10, then counts for 40 of the 100.
2. Extraction and analysis
15 of 100 pointsOnce papers are included, can it pull their data into a table, and show the passage every answer came from?
Pulls data from many papers into a tableup to 3
Answers show the passage they came fromup to 2
Ask questions of a paperup to 2
Summarises papersup to 1.5
Reads tables and figuresup to 1.5
Each section adds up to 10, then counts for 15 of the 100.
3. Teams, access and privacy
15 of 100 pointsCan the whole team screen in shared projects, can your university or library license it, and does it keep your uploads out of its AI training?
Shared projects with your teamup to 3.5
University or library licenceup to 3
Works in languages other than Englishup to 0.5
Does not train AI on your dataup to 1
| Yes | +1 |
| Only if you opt out | +0.5 |
| No | 0 |
Each section adds up to 10, then counts for 15 of the 100.
4. Pricing
15 of 100 pointsWhat the cheapest plan costs, at the academic rate where the vendor publishes one, or by the year where it only sells yearly.
Tools charge in different ways, so there is one price table for each. Only the table that matches how a tool charges counts, so a fee per use or a yearly price is never compared with a monthly plan.
Monthly price, cheapest paid plan (academic rate if offered)up to 10
| Free | +10 |
| Up to $10 | +9 |
| Up to $15 | +8 |
| Up to $20 | +7 |
| Up to $30 | +5.5 |
| Up to $50 | +4 |
| Up to $80 | +2.5 |
| Over $80 | +1 |
Yearly price, sold by the year onlyup to 10
| Free | +10 |
| Up to $120 | +9 |
| Up to $180 | +8 |
| Up to $240 | +7 |
| Up to $360 | +5.5 |
| Up to $600 | +4 |
| Up to $960 | +2.5 |
| Over $960 | +1 |
Each section adds up to 10, then counts for 15 of the 100.
5. Finding papers
10 of 100 pointsCan it also search for papers, or do you bring the references in from the databases yourself? Most review teams do the latter, so this carries fewer points.
Searches a database of papersup to 4
Answers a research question from the literatureup to 2
Map of connected papersup to 1.5
Alerts for new papersup to 1.5
Shows if later papers support or dispute a paperup to 1
Each section adds up to 10, then counts for 10 of the 100.
6. Citing and exports
5 of 100 pointsDoes it work with your reference manager and export in the formats you need?
Works with Zotero, Mendeley, EndNote and othersup to 4
| None | 0 |
| 1 reference manager | +2.5 |
| 2 reference managers | +3.5 |
| 3 reference managers or more | +4 |
Export formatsup to 3.5
| None | 0 |
| 1 format | +1.5 |
| 2 formats | +2.5 |
| 3 formats or more | +3.5 |
Browser extensionup to 1.25
Word or Google Docs add-inup to 1.25
Each section adds up to 10, then counts for 5 of the 100.
A real example: Rayyan
Here is how Rayyan got its 8.2.
| Section | Points |
|---|
| Running the review | 40 of 40 |
| Extraction and analysis | 10.5 of 15 |
| Teams, access and privacy | 14.3 of 15 |
| Pricing | 13.5 of 15 |
| Finding papers | 2 of 10 |
| Citing and exports | 1.8 of 5 |
| Total | 82.1 of 100 = 8.2 out of 10 |
See every fact behind Rayyan's score.
When a tool doesn't say
If a tool's website doesn't answer a yes-or-no question, it gets half the points for that item. Not zero, because a missing answer isn't the same as a no, and not full marks, because silence shouldn't beat a vendor who answers honestly. For a number, like a price, it gets the typical value of the tools that do publish one. Every item scored this way is marked on the tool's scorecard.
If a tool leaves out more than a third of what we check, we don't show a score for it at all. A number built mostly on guesses wouldn't be fair to you or to the tool. Right now 23 of the 23 tools we checked have enough information to be scored.
What the score doesn't tell you
We score what a tool offers and what it costs, as its own website describes it. That's not a hands-on test. The score can't tell you whether a tool is easy to use, whether its data is accurate, or whether support answers quickly. The review covers that.
See the AI Research tools ranked or read how we review tools in general.