Agent Testing Network
50 agents continuously test every API in our directory across 10 domains. Every test is public, reproducible, and auditable. Watch them work.
Methodology
50
Benchmark agents across 10 domains
499
Standardized queries (simple → complex)
31,081
Total benchmark tests run
Agents — 50 agents using Claude, GPT-4, Gemini, DeepSeek, and Llama model families
Queries — 499 standardized queries across 10 domains, graded by complexity
Evaluation — LLM-judged relevance, freshness, and completeness (0–5 scale)
Frequency — Every 2 hours, automated via cron
Benchmarks by Domain
Recent Batch Comparisons
8a51be13…embeddingembedding best practices for query-embed (7)2 toolsOct 29, 02:00 AM▼
| Tool | Relevance | Freshness | Completeness | Latency | Results |
|---|---|---|---|---|---|
| Voyage Embeddings | 2.0/5 | 3.0/5 | 5.0/5 | 110ms | 1 |
| Jina Embeddings | 0.0/5 | 0.0/5 | 0.0/5 | 312ms | 0 |
fce71b40…crawlingfind primary sources about static-html in crawling (5)5 toolsOct 29, 01:30 AM▼
| Tool | Relevance | Freshness | Completeness | Latency | Results |
|---|---|---|---|---|---|
| Apify | 0.0/5 | 0.0/5 | 0.0/5 | 524ms | 0 |
| ScrapingBee | 0.0/5 | 0.0/5 | 0.0/5 | 493ms | 0 |
| Browserbase | 0.0/5 | 0.0/5 | 0.0/5 | 0ms | 0 |
| Firecrawl | 0.0/5 | 0.0/5 | 0.0/5 | 340ms | 0 |
| Jina AI | 0.0/5 | 0.0/5 | 0.0/5 | 116ms | 1 |
dffe6aec…finance_dataGOOGL3 toolsOct 29, 01:00 AM▼
| Tool | Relevance | Freshness | Completeness | Latency | Results |
|---|---|---|---|---|---|
| Polygon.io | 2.0/5 | 3.0/5 | 1.6/5 | 205ms | 1 |
| Alpha Vantage | 2.0/5 | 3.0/5 | 5.0/5 | 354ms | 100 |
| Financial Modeling Prep | 0.0/5 | 0.0/5 | 0.0/5 | 238ms | 0 |
98dc9172…multilingualmultilingual best practices for translation (2)2 toolsOct 29, 12:30 AM▼
| Tool | Relevance | Freshness | Completeness | Latency | Results |
|---|---|---|---|---|---|
| Exa Search | 5.0/5 | 3.0/5 | 5.0/5 | 348ms | 10 |
| Tavily | 0.0/5 | 0.0/5 | 0.0/5 | 210ms | 0 |
3b2457f4…generallatest general changes affecting research (1)2 toolsOct 29, 12:00 AM▼
| Tool | Relevance | Freshness | Completeness | Latency | Results |
|---|---|---|---|---|---|
| Exa Search | 5.0/5 | 3.0/5 | 5.0/5 | 328ms | 10 |
| Tavily | 0.0/5 | 0.0/5 | 0.0/5 | 258ms | 0 |
Recent Tests
🔬Voyage Embeddingsembedding best practices for query-embed (7)
110ms
🔬Polygon.ioGOOGL
205ms
🔬Alpha VantageGOOGL
354ms
🔬Exa Searchmultilingual best practices for translation (2)
348ms
🔬Exa Searchlatest general changes affecting research (1)
328ms
🔬Exa Searchscience regulations impacting breakthroughs (19)
300ms
🔬Exa Searchcompare top tools for politics workflows (18)
336ms
🔬Exa Searchlatest education changes affecting curriculum (16)
326ms
Benchmarks by Task
Reproduce These Tests
All benchmark configurations are public. Your agent can download query sets and reproduce any test with its own infrastructure.