See how much smarter your AI could be by adding tools
We independently measure the tools AI agents use and publish what each one actually adds.
Agentic Search Indexi
MethodologyAgentic Search Index v0.1 · Jul 2026
Highlights
Accuracy, cost, and speed for every tool, measured the same way.
Agentic Search Indexi
The overall score: how often each tool finds the right answer.
Costi
USD per 1,000 successful answers
Speedi
How long your agents wait for each search.
Check your own setup
Your agent already knows which tools you run. Paste one prompt and it checks that setup against the measured data, then tells you in plain words what would actually help.
Which search tool is right for your agents?
No tool wins everything: match each tool's strengths to the questions your agents actually ask.
Correct Answers by Question Typei
From deep research to finding current info, each tool has its strengths.
Failure Attributioni
Know how each tool tends to fail before your agent depends on it.
Agentic Memory Index
Eight memory tools measured on simulated multi-week company brain operations.
The bottom line
Rankings on the left, real costs on the right.
Every tool's score, cost, and speed in one table.
| # | Service | Index (CI) | Cost / 1k | p50 / p95 |
|---|---|---|---|---|
| 1 |  Firecrawl |
82.9 (78.7–86.4) | $37.94 | 2.0s / 5.0s |
| 2 |  Serper |
80.9 (76.6–84.7) | $14.46 | 1.0s / 1.7s |
| 3 |  Tavily |
78.1 (73.4–82.1) | $58.54 | 6.0s / 9.1s |
| 4 |  Parallel Pro |
77.1 (72.2–81.4) | $55.25 | 2.4s / 4.0s |
| 5 |  Exa |
75.9 (71.2–80.1) | $69.70 | 1.9s / 2.7s |
| 6 |  Brave |
75.2 (70.5–79.4) | $125.55 | 0.7s / 1.0s |
| 7 |  Linkup |
72.5 (67.5–77.0) | $76.43 | 2.3s / 4.2s |
| 8 | Parallel Base |
71.8 (66.6–76.5) | $84.12 | 1.8s / 3.5s |
| — | Claude native WebSearch baseline | 69.1 | $30.19 | — |
| 9 |  Perplexity Sonar |
67.2 (61.9–72.0) | $48.69 | 3.7s / 8.0s |
Cost Breakdowni
The fee per call is often less than the token cost of reading what comes back.