Updated

DeepEval

Open-source Python framework for unit-testing LLM apps with pytest-style test cases and ready-made metrics (faithfulness, answer relevancy, hallucination, G-Eval), from Confident AI.

12 open-source projects declare DeepEval in their code; no maker's live product we track uses it yet.

Open sourceSelf-hostableFree tierPaid from $200/mo (Confident AI Starter)

Profile checked

Works with AI agents:llms.txtCLI
Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use DeepEval

What DeepEval is used for

LLM Observability & Evals · Eval and test CLI →Writing LLM evals as pytest-style tests in Python, with ready-made metrics for hallucination, faithfulness and answer relevancy.Trade-off: The metrics use an LLM as a judge, so every run costs tokens and scores vary slightly; dashboards and history are in the paid Confident AI platform.
Datadog50Langfuse35Helicone13LangSmith11Braintrust6DeepEval0Makers' products on each, for LLM observability & evals

DeepEval vs the alternatives makers chose

OptionMakers' productsFree forAt 10,000 usersOpen source
Datadog50 43%——No
Langfuse35 30%~5,000 users$29/mo · CoreYes
Helicone13 11%~1,000 users$116/mo · ProYes
LangSmith11 9%~520 users$475/mo · DeveloperNo
Braintrust6 5%——No
Weights & Biases3 3%——No
DeepEval0 0%Any size—Yes

For LLM observability & evals: how many of the 117 makers' products we know the LLM observability & evals of chose each option, and what each costs at 10,000 users.

Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.

When to use DeepEval, and when not

Something else fits better if

  • You want tracing, prompts and evals in one tool you can self-host for free: Langfuse.
  • You already use OpenTelemetry or want vendor-neutral instrumentation: Arize Phoenix.
  • You want request logs and costs today by changing one base URL: Helicone.
  • Your app is built on LangChain or LangGraph: LangSmith.
  • Your main question is whether a prompt or model change made outputs better or worse: Braintrust.
From each decision's guide, written from what makers' products chose and why.

How DeepEval itself is built

21 tools, from its own code, website and Product Hunt page.

Reliability and open issues

The most wanted open issue on GitHub has 16 👍.

Most wanted on GitHub

Open on 2026-10-04 in confident-ai/deepeval, with activity in the last year — issues and feature requests by 👍.

Who uses it

No maker's live product on record yet, and 12 open-source projects that declare it in their code.

We haven't found a maker's live product that uses DeepEval yet — only the open-source projects below, which declare it in their code.

MLflow
MLflowOpen-source platform for the ML and GenAI lifecycle — experiment tracking, a model regis…LLM Observability & EvalsIn its code · source ↗

Open source: a project that declares DeepEval as a dependency in its public code — verifiable, but not necessarily a live product.

Alternatives to DeepEval

All alternatives by situation →

Questions makers ask about DeepEval

What are the alternatives to DeepEval?

For LLM observability & evals, the other options makers' products we track chose most are Datadog (50), Langfuse (35), Helicone (13), LangSmith (11), Braintrust (6), Weights & Biases (3). Open source or self-hostable among them: Langfuse, Helicone, Weights & Biases. Each alternative, with the situation it fits, is on the DeepEval alternatives page.

Is DeepEval free?

Yes — there is a free tier a small product can run on; paid use starts at $200/mo (Confident AI Starter). source ↗

Is DeepEval open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with DeepEval?

It serves an llms.txt docs index; it has an official CLI (deepeval).

Who uses DeepEval?

No maker's live product we track yet; 12 open-source projects declare it in their code. source ↗