# Nava UGC creator sourcing benchmark: which tool finds UGC creators who are really your customer?

Updated 2026-11-05. Status: scored.

For briefs about who a creator is, which tool returns more TikTok creators who really are that customer and still get watched, and at what cost per creator?

- Page: https://meetnava.com/benchmarks
- Data (JSON, every number): https://meetnava.com/benchmarks.json
- License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
- How to cite: Nava (2026). Nava UGC creator sourcing benchmark, run 1. https://meetnava.com/benchmarks.json
- Judge: Jev (TypeSafe, jev-1.14.0), a grading model from another company that none of the tools uses to pick creators. It sees the brief's must-haves and the creator's bio and recent posts, not which tool found them.

## Results

Nava won **8 of 12** briefs against the best creator database and **8 of 12** against an AI agent working alone. The bar set before the run was 10 of 12 for each, so **neither bar was met**. The kill rule (fewer than 7 wins against the databases) did not trigger.

| Tool | Qualified creators | Exact in top 5s | Top-5 picks | Tool spend | With buyer's checking | Cost per qualified |
|---|---|---|---|---|---|---|
| Nava | 30 | 30 | 56 | $22.75 | $22.75 | $0.76 |
| AI agent alone | 7 | 25 | 60 | $4.67 | $49.68 | $7.10 |
| Influencers.club | 2 | 19 | 58 | $3.39 | $46.89 | $23.44 |
| Exa | 1 | 20 | 60 | $0.32 | $45.36 | $45.36 |

### By brief

| Brief | Tool | Exact in top 5 | Qualified | Spend | With buyer's checking | Cost per qualified |
|---|---|---|---|---|---|---|
| 1 | Nava | 5/5 | 5 | $1.13 | $1.13 | $0.23 |
| 1 | Influencers.club | 3/5 | 1 | $0.30 | $4.05 | $4.05 |
| 1 | Exa | 4/5 | 0 | $0.03 | $3.78 | none found |
| 1 | AI agent alone | 4/5 | 2 | $0.32 | $4.07 | $2.03 |
| 2 | Nava | 0/5 | 0 | $2.21 | $2.21 | none found |
| 2 | Influencers.club | 0/5 | 0 | $0.30 | $4.05 | none found |
| 2 | Exa | 2/5 | 0 | $0.03 | $3.78 | none found |
| 2 | AI agent alone | 0/5 | 0 | $0.37 | $4.12 | none found |
| 3 | Nava | 4/5 | 4 | $0.91 | $0.91 | $0.23 |
| 3 | Influencers.club | 5/5 | 0 | $0.30 | $4.05 | none found |
| 3 | Exa | 4/5 | 0 | $0.03 | $3.78 | none found |
| 3 | AI agent alone | 4/5 | 0 | $0.34 | $4.09 | none found |
| 4 | Nava | 5/5 | 5 | $0.68 | $0.68 | $0.14 |
| 4 | Influencers.club | 4/5 | 1 | $0.30 | $4.05 | $4.05 |
| 4 | Exa | 3/5 | 0 | $0.03 | $3.78 | none found |
| 4 | AI agent alone | 3/5 | 0 | $0.26 | $4.01 | none found |
| 5 | Nava | 5/5 | 5 | $0.71 | $0.71 | $0.14 |
| 5 | Influencers.club | 4/5 | 0 | $0.30 | $4.05 | none found |
| 5 | Exa | 3/5 | 1 | $0.03 | $3.78 | $3.78 |
| 5 | AI agent alone | 4/5 | 1 | $0.43 | $4.18 | $4.18 |
| 6 | Nava | 2/5 | 2 | $1.06 | $1.06 | $0.53 |
| 6 | Influencers.club | 1/5 | 0 | $0.30 | $4.05 | none found |
| 6 | Exa | 1/5 | 0 | $0.03 | $3.78 | none found |
| 6 | AI agent alone | 1/5 | 1 | $0.32 | $4.07 | $4.07 |
| 7 | Nava | 0/5 | 0 | $4.00 | $4.00 | none found |
| 7 | Influencers.club | 0/5 | 0 | $0.30 | $4.05 | none found |
| 7 | Exa | 0/5 | 0 | $0.03 | $3.78 | none found |
| 7 | AI agent alone | 0/5 | 0 | $0.34 | $4.09 | none found |
| 8 | Nava | 5/5 | 5 | $1.35 | $1.35 | $0.27 |
| 8 | Influencers.club | 1/5 | 0 | $0.30 | $4.05 | none found |
| 8 | Exa | 1/5 | 0 | $0.03 | $3.78 | none found |
| 8 | AI agent alone | 3/5 | 0 | $0.37 | $4.12 | none found |
| 9 | Nava | 3/5 | 3 | $3.24 | $3.24 | $1.08 |
| 9 | Influencers.club | 0/5 | 0 | $0.30 | $4.05 | none found |
| 9 | Exa | 0/5 | 0 | $0.03 | $3.78 | none found |
| 9 | AI agent alone | 1/5 | 1 | $0.37 | $4.12 | $4.12 |
| 10 | Nava | 0/5 | 0 | $3.24 | $3.24 | none found |
| 10 | Influencers.club | 0/5 | 0 | $0.09 | $2.34 | none found |
| 10 | Exa | 0/5 | 0 | $0.03 | $3.78 | none found |
| 10 | AI agent alone | 1/5 | 1 | $0.57 | $4.32 | $4.32 |
| 11 | Nava | 0/5 | 0 | $2.97 | $2.97 | none found |
| 11 | Influencers.club | 0/5 | 0 | $0.30 | $4.05 | none found |
| 11 | Exa | 1/5 | 0 | $0.03 | $3.78 | none found |
| 11 | AI agent alone | 4/5 | 1 | $0.42 | $4.17 | $4.17 |
| 12 | Nava | 1/5 | 1 | $1.25 | $1.25 | $1.25 |
| 12 | Influencers.club | 1/5 | 0 | $0.30 | $4.05 | none found |
| 12 | Exa | 1/5 | 0 | $0.03 | $3.78 | none found |
| 12 | AI agent alone | 0/5 | 0 | $0.57 | $4.32 | none found |

| Brief | vs databases | vs AI agent alone |
|---|---|---|
| 1 | win | win |
| 2 | loss | loss |
| 3 | win | win |
| 4 | win | win |
| 5 | win | win |
| 6 | win | win |
| 7 | loss | loss |
| 8 | win | win |
| 9 | win | win |
| 10 | loss | loss |
| 11 | loss | loss |
| 12 | win | win |

## Notes on the run

- Each tool was run once, not twice, to keep within the data budget. Run-to-run noise wasn't measured, so no brief could be scored a tie on noise.
- Nava's TikTok calls went through treg instead of Monid (same endpoints and prices) after a first attempt timed out; that attempt's results were discarded. Brief 7 was re-graded from its saved search data after a parsing fix. All of this happened before any results were seen.

## Pre-registered bar

Pre-registered on 2026-11-05, before any of the 12 briefs was run (one dry run on a practice brief came first and doesn't count). Nava wins a brief if its precision is at least the best of Influencers.club and Exa, and its cost per qualified creator is a third of that tool's or less (or it finds qualified creators and that tool finds none). The headline claim needs wins on at least 10 of the 12 briefs, including a control Nava is expected to lose. Against the AI agent alone, Nava must find more qualified creators at no more cost on at least 10 of 12; if not, search alone is not a moat. Each tool runs twice; a gap no bigger than a tool's own run-to-run swing is a tie. If Nava wins fewer than 7 of 12 against the databases, Nava stops claiming better matches.

## Tools compared

- **Nava**: Nava's own pipeline: searches TikTok, keeps creators who posted in the last 30 days with typical views at least 0.3x followers, and grades each one against the brief from their own bio and posts.
- **Influencers.club**: A creator database with an API and an MCP server. Its own plain-language reading of the brief, with the follower range. Top 10.
- **Exa**: AI web search, pinned to tiktok.com, given the brief as written. Top 10 creators.
- **AI agent alone**: Claude with the same raw TikTok search, profile and video tools Nava uses, the brief and a $0.50 data budget, but none of Nava's code or rules. Top 10.

## Method

- The same 12 briefs went to all four tools on the same day.
- Each tool's top 5 creators per brief were pooled, duplicates merged and the order shuffled.
- One judge, Jev (TypeSafe, jev-1.14.0), graded the whole pool the same way: exact, close or no, from the brief's must-haves and each creator's bio and recent posts, without knowing which tool found them. None of the tools uses Jev to pick creators.
- Every creator from every tool got the same activity and views check: posted in the last 30 days, typical views at least 0.3x followers.
- Costs are what each tool spent on data and AI, plus the buyer's time to vet by hand for tools that don't vet.

## Definitions

- **exact**: The judge says the creator's own bio or posts show every must-have in the brief (each must-have at least 0.5 likely, and under 0.5 likely not a real person living it).
- **qualified**: Exact, and posted in the last 30 days, and typical views on recent posts are at least 0.3x their follower count. The same check runs on every tool's creators.
- **precision**: Share of a tool's top 5 that the judge called exact.
- **cost_per_qualified_usd**: What the tool spent on data and AI, plus the buyer's time to vet its top 5 by hand at 1.5 minutes each and $30 an hour for tools that don't vet, divided by qualified creators in its top 5.
- **UGC creator**: Someone paid by a brand to make videos in their own voice (user-generated content), usually for ads or the brand's own accounts.
- **Customer-creator**: A creator who is the brand's customer: a nurse for a scrubs brand, a salesperson for a sales tool. That is the kind of creator this benchmark looks for.
- **Brief**: Who the creators should be, in plain words, with the must-haves spelled out. Example: "registered dietitians".
- **Must-have**: Something the creator's own bio or posts have to show for them to count. A guess from looks or follower count doesn't count.
- **Judge**: The model that graded every creator the same way, without knowing which tool found them: Jev (TypeSafe, jev-1.14.0), a grading model from another company that none of the tools uses to pick creators. It sees the brief's must-haves and the creator's bio and recent posts, not which tool found them.
- **Pre-registered bar**: The rule for what counts as a win, written down and fixed before the tools ran, so it can't be moved to fit the results.
- **Control brief**: A brief built to test a weakness on purpose: one where almost nobody fits, one about something that just happened, and one where the databases should win.

## Briefs

| # | Who | Must have | Shows up in | How many exist | Note |
|---|---|---|---|---|---|
| 1 | dog or cat owners whose pets are in their videos | owns a dog or cat; the pet appears in their own videos | bio | many |  |
| 2 | certified personal trainers who train clients | is a certified personal trainer; trains clients now | bio | many |  |
| 3 | dermatologists or licensed estheticians | is a board-certified dermatologist or a licensed esthetician; practices now | bio | few |  |
| 4 | registered dietitians | is a registered dietitian (RD/RDN) | bio | few |  |
| 5 | people paying off debt and sharing their progress | is paying off their own debt; shares their own numbers or progress | posts | many |  |
| 6 | people aged about 25 to 50 who lift weights regularly | appears to be about 25 to 50; lifts weights regularly, shown in their own videos | posts | many |  |
| 7 | small business owners who answer their own phone calls | owns and runs a small business; handles customer phone calls themselves | posts | many |  |
| 8 | parents of kids with food allergies | is a parent; their own child has a food allergy | posts | few |  |
| 9 | people who talk openly about living with anxiety and going to therapy | says themselves that they live with anxiety; talks about their own therapy | posts | few |  |
| 10 | ER nurses who work nights in Boise, Idaho | works as an ER nurse; works night shifts; lives or works in or near Boise, Idaho | posts | very few | Control: almost nobody fits, tests padding |
| 11 | people laid off in the last 60 days who are job hunting | was laid off within about the last 60 days; is looking for a job now | posts | many | Control: recent event, tests stale indexes |
| 12 | US fitness creators with 100K to 500K followers | makes fitness content; is based in the US | bio | many | Control: the databases' home turf, Nava should lose |

## Limits

- TikTok only.
- 12 briefs, top 5 per tool, one judge, one run. Treat any single brief's result as noisy.
- The briefs were written by Nava from real buyer requests (job posts, app founders, site searches). Two briefs used to build Nava were set aside and don't count.
- Nava's grading rules and the judge's rules are close, which favors Nava. The judge sees the same must-haves for every tool.
- Influencers.club's and Exa's queries are each tool's own reading of the brief as written, not tuned by an expert.
- Nava spends more on data and AI per brief than the other tools. It comes out cheaper per qualified creator only because it finds more of them and the others' picks have to be checked by hand.

## FAQ

### How do I find UGC creators who are really my customer?

Start from who they are, not from follower counts. Look for creators whose own bio or posts say it: a nurse who posts about her night shifts, an account executive who films his prospecting block. Then check that they still post (the last 30 days) and still get watched (typical views on recent posts at least 0.3x their followers), and read the profile yourself before you reach out. Nava does this for you: tell it who your customer is and it sends the creators who fit, each checked against their own bio and posts.

### Which tool found the most UGC creators who are really the customer?

In this benchmark, Nava: 30 qualified creators across the top 5s of 12 TikTok briefs, against 7 for an AI agent working alone with the same data, 2 for Influencers.club and 1 for Exa. Nava won 8 of 12 briefs against the databases and 8 of 12 against the agent. The bar set before the run was 10 of 12, so it was not met.

### Why do creator databases score so low?

Most of their picks are the right kind of person but have stopped posting or no longer get watched. The judge called 19 of Influencers.club's top picks and 20 of Exa's exact, but only 2 and 1 of those passed the activity and views check.

### Where did Nava fail?

On 4 briefs Nava found no qualified creator: certified personal trainers who train clients; small business owners who answer their own phone calls; ER nurses who work nights in Boise, Idaho; people laid off in the last 60 days who are job hunting. Neither database found one either. The AI agent alone found one each on two of them, the near-empty Boise control and recent layoffs.

### How does Nava check that a creator is the customer?

Nava searches TikTok for the brief, then reads each creator's own bio and recent posts and grades them against every must-have: exact, close or no. It keeps only creators who posted in the last 30 days with typical views at least 0.3x followers. In two earlier blind checks (ER nurses who work nights; people who sell for a living), every creator Nava's grader called exact, 13 of 13, was also called exact by a person. That is a small sample, so Nava says "checked against their own bio and posts", not "verified".

### How was this comparison run?

Four tools (Nava, Influencers.club, Exa and an AI agent working alone with the same TikTok data) got the same 12 briefs on the same day. Each tool's top 5 per brief were pooled, shuffled and graded by one judge, Jev (TypeSafe), a model none of the tools uses, without knowing which tool found each creator. Every creator got the same activity and views check. The bar for a win was fixed before the briefs were run.

### Why compare Nava with an AI agent working alone?

To test whether Nava adds anything an agent can't do itself with the same raw TikTok search, profile and video tools. The bar was 10 of 12 briefs; Nava won 8, so by the rule set in advance, search alone isn't yet a moat.

### Can I use or cite this data?

Yes, under CC BY 4.0. Cite it as: Nava (2026). Nava UGC creator sourcing benchmark, run 1. https://meetnava.com/benchmarks.json. The JSON file has every brief, definition, the bar and every result row.

### Can an AI agent order creators from Nava?

Yes. Nava has an MCP server at https://meetnava.com/mcp (no key) and the same tools as REST, described at https://meetnava.com/openapi.json. find_creators returns creators Nava already checked at once and queues a fresh graded search.