Firecrawl vs. Tavily vs. Exa vs. DeepSeek
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
Hrih News covers a blind test of four search APIs built for AI agents (Exa, Firecrawl, Tavily and DeepSeek) on 40 searches, 40 page fetches and two site crawls, run on 23 October 2026.
Score
0.65total under rubric v2.0Contestedjudges differ by 0.48 on new information
- Significance0.50
- Reader interest0.78
- Audience breadth0.58
- Practical relevance0.88
- Substantiated0.82
- Technical depth0.82
- New information0.79
- Counts against: Promotional0.13
- Counts against: Overclaim0.30
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| Significance | 0.53 | 0.30 | 0.68 | 0.50 | 0.38 | +0.25 | +0.125 |
| Reader interest | 0.69 | 0.70 | 0.95 | 0.78 | 0.26 | +0.20 | +0.156 |
| Audience breadth | 0.51 | 0.50 | 0.72 | 0.58 | 0.22 | +0.10 | +0.058 |
| Practical relevance | 0.97 | 0.80 | 0.88 | 0.88 | 0.17 | +0.15 | +0.132 |
| Substantiated | 0.93 | 0.70 | 0.82 | 0.82 | 0.23 | +0.10 | +0.082 |
| Technical depth | 0.99 | 0.70 | 0.78 | 0.82 | 0.29 | +0.10 | +0.082 |
| New information | 0.88 | 0.50 | 0.98 | 0.79 | 0.48 , above the contested threshold | +0.10 | +0.079 |
| Promotional | 0.05 | 0.30 | 0.05 | 0.13 | 0.25 | −0.15 | −0.020 |
| Overclaim | 0.27 | 0.40 | 0.22 | 0.30 | 0.18 | −0.15 | −0.045 |
| Sum of contributions | +0.650 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.649 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 2 pts, not on front page
Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.