# Coralogix Telemetry Lake Benchmarks

> Live observability benchmarks from Coralogix: query latency percentiles (p50, p90, p95) measured on Coralogix's own production telemetry lake, a comparison of how AI agents investigate incidents across five observability platforms (Coralogix, Datadog, Dynatrace, Grafana Cloud, New Relic) on the same budget, and an interactive tour of Streama, Coralogix's Kafka-based processing engine.

Published by Coralogix (https://coralogix.com). Figures update every 5 minutes; cite them with the time they were measured.

## Current figures

Measured 2026-10-10 19:00:00 UTC, refreshed every 5 minutes. Query window: the last 7 days (2026-10-03T19:00:00Z to 2026-10-10T19:00:00Z).

### Global stats, past 7 days (every Coralogix environment)

- Ingested into Coralogix in the last 7 days: 44.1 PB
- Telemetry lake queries in the last 7 days: 3.99 billion
- Regions (inc. GovCloud): 9

### A large scale single account benchmark

A scaled account ingesting 40 TB a day, 1.2 PB queryable and 1.12 billion timeseries of metrics.

| Queries, last 7 days | Queries | p50 latency | p90 latency | p95 latency |
|---|---|---|---|---|
| Logs, Spans, SIEM, RUM, AI sessions (DataPrime) | 157,799 | 998 ms | 5.3 s | 12 s |
| Custom metrics, Infra, APM metrics (PromQL) | 372,751,322 | 13 ms | 197 ms | 440 ms |

### A medium scale single account benchmark

A mid size account ingesting 300 GB a day, 9 TB queryable and 2 million timeseries of metrics.

| Queries, last 7 days | Queries | p50 latency | p90 latency | p95 latency |
|---|---|---|---|---|
| Logs, Spans, SIEM, RUM, AI sessions (DataPrime) | 60,737 | 341 ms | 717 ms | 871 ms |
| Custom metrics, Infra, APM metrics (PromQL) | 7,047,836 | 15 ms | 205 ms | 260 ms |

## Observability Vendor Comparison: AI agents on the same budget

A rigorous investigation into how different observability platforms, given the same budget, make AI agents smarter. Coralogix, Datadog, Dynatrace, Grafana Cloud and New Relic each received the share of the OpenTelemetry Astronomy Shop Demo's telemetry that the same illustrative $10,000/month budget buys at public list prices. AI agents then investigated 10 scenarios, rated from easy to hardest, on every platform, with five investigations per platform in each.

Outcome: Coralogix agents scored highest on both root cause analysis and impact measurement. Average scores across the 9 fault scenarios, weighted equally (the tenth, Optimize, looks for improvements rather than a fault, so it has no cause or impact score):

| Platform | Root cause analysis | Impact measurement | Combined |
|---|---|---|---|
| Coralogix | 99.1% | 90.6% | 92.5% |
| Grafana Cloud | 77.8% | 75.0% | 72.3% |
| New Relic | 82.9% | 63.7% | 67.8% |
| Dynatrace | 77.8% | 63.1% | 67.7% |
| Datadog | 63.6% | 57.2% | 56.0% |

We found that keeping complete telemetry helped agents explain why a problem happened and measure its impact more accurately. The full method, pricing calculations, per-scenario results, false claims and caveats are on the page.

## Pages

- [Coralogix Benchmarks](https://benchmarks.coralogix.com/): the home page, with a way into each of the pages below
- [Coralogix Telemetry Lake Benchmarks](https://benchmarks.coralogix.com/benchmarks.md): live observability benchmarks, query latency (p50, p90, p95) for DataPrime and PromQL on a large and a medium account, and how the telemetry lake works
- [Observability Vendor Comparison](https://benchmarks.coralogix.com/observability-vendor-comparison.md): Coralogix vs Datadog, Dynatrace, Grafana Cloud and New Relic, AI agents investigating 10 incident scenarios on the same $10,000/month budget, with method, pricing calculations, results and caveats
- [Streama Explorer](https://benchmarks.coralogix.com/streama.md): a guided tour of Streama, Coralogix's Kafka-based stream processing engine

## Data

- [Benchmarks API](https://benchmarks.coralogix.com/api/v1/benchmarks): the current snapshot as JSON (accounts.large and accounts.small: q1 percentiles by dataset, query type and volume; q2 hourly series; metrics; estate: 7-day totals)

## Optional

- [Everything in one file](https://benchmarks.coralogix.com/llms-full.txt)
- [Coralogix](https://coralogix.com/)