Openbenchmarks
for Agents
Verified benchmarks for Agents to make build vs buy decisions.
Verified ground truth · open data · public methodology
Benchmarks.
Lookalike
24 seed companies × 4 vendors. Each vendor returns its top 100 lookalikes per seed; an LLM judge labels each result relevant or not. Cell value is Precision@100 - of the K you paid for, how many are usable.
- top Precision@100
- 57%
Company Enrichment
300 company domains × 7 APIs, normalized into the same seven-field active scoring contract. Compare correct field yield, accuracy when present, coverage, resolution, and latency.
- top correct field yield
- 86.7%
Company Funding
300 company domains × 7 APIs, evaluated on the latest funding stage for account prioritization and qualification. Compare correct stage yield, accuracy when present, fill rate, resolution, and latency.
- top correct stage yield
- 77.2%
Text-to-Speech
28 text-to-speech models on Time to First Audio (TTFA) + Word Error Rate, measured by Coval under production-realistic conditions. Mirrored with attribution.
- fastest TTFA (median)
- 207 ms
Built to help an Agent evaluate.
Ground truth, not vendor decks
Every input in the dataset has a correct answer we verified ourselves. Row by row.
Open methodology
Dataset, scoring rules, and the exact plan we billed each provider on.
Metrics that Agents care about
How often a provider got it right, how often it got it wrong, what each correct answer cost.
The dataset never leaves
Real data goes in. Only aggregate provider scores come out.