Who should use nooa-bench?

nooa-bench is an open-source project built for developers.

Does nooa-bench have a free plan?

Yes — nooa-bench is open source under the Apache-2.0 license and free to use.

What platforms does nooa-bench run on?

nooa-bench runs on the command line.

Is nooa-bench still maintained?

The GitHub repository shows 109 commits in the last 90 days.

What are alternatives to nooa-bench?

Similar projects tracked by PulseGate include constraintloop, trajectory-judge, and DeFake.

Who develops nooa-bench?

nooa-bench is developed by NVIDIA NeMo.

How long has nooa-bench been around?

nooa-bench first shipped in 2026.

Back to the index

nooa-bench

Name: nooa-bench
Author: NVIDIA NeMo

PyPIInfrastructure

nooa-bench provides a benchmark agent (BenchAgent) and Harbor runner specifically for the NOOA framework. It is designed to reproduce the results from the technical report on SWE-bench and Terminal-Bench. The package enables standardized evaluation of code-generating AI agents through reproducible benchmarking tools.

Open SourceApache-2.0CLI

Visit PyPI

512stars

75forks

4features

2026since

Overview

4 features

In the LLM eval & observability space, nooa-bench takes a focused approach. It focuses on reproducing and running standardized benchmarks for code-generating AI agents in the NOOA framework. It is built as an open-source project for developers. The project is open source (Apache-2.0). It ships for the command line.

Behind nooa-bench is NVIDIA NeMo, and it first shipped in 2026. Development happens publicly on GitHub with 512 stars and 109 commits in the last 90 days. Key capabilities include Benchmark Runner, SWE-Bench, and terminal-Bench.

Summary written by a language model from the project’s public pages.

Benchmark Runner
SWE-Bench
Terminal-Bench
Evaluation

Built with & integrations

Framework

FastAPI

AI providers

multiple

Runs on

CLI

Trust & compliance

License

Apache-2.0

Verified signals

HTTPSOpen SourceActive maintenance

Indexing history

What PulseGate has recorded for this listing

Indexed30 Jul · 06:32 UTC
nooa-bench verified against its public source
Source: PulseGate · Open

Frequently asked questions about nooa-bench

What is nooa-bench?: Nooa-bench focuses on reproducing and running standardized benchmarks for code-generating AI agents in the NOOA framework. It is catalogued under LLM eval & observability on PulseGate.
Who should use nooa-bench?: nooa-bench is an open-source project built for developers.
Does nooa-bench have a free plan?: Yes — nooa-bench is open source under the Apache-2.0 license and free to use.
What platforms does nooa-bench run on?: nooa-bench runs on the command line.
Is nooa-bench still maintained?: The GitHub repository shows 109 commits in the last 90 days.
What are alternatives to nooa-bench?: Similar projects tracked by PulseGate include constraintloop, trajectory-judge, and DeFake.constraintloop trajectory-judge DeFake
Who develops nooa-bench?: nooa-bench is developed by NVIDIA NeMo.
How long has nooa-bench been around?: nooa-bench first shipped in 2026.

At a glance

Platforms: Cli
Languages: English
License: Apache-2.0
First seen: 30 Jul 2026
Built for: developers
Model: Open source
Solves: Reproducing and running standardized benchmarks for code-generating AI agents in the NOOA framework.

Registered as

PyPI: nooa-bench

Developer

NVIDIA NeMo

Team

Open source

Stars: 512
Forks: 75
Open issues: 11
Last commit: 30 Jul 2026
Commits 90d: 109
Contributors: 7
Authorship: Team
Default branch: main
Latest release: v0.0.7 · 30 Jul 2026

Live coverage

Identity confidence: Low · 64
Indexed: 30 Jul 2026
Lifecycle: Alive
First seen: Jul 2026
Last seen: 30 Jul 2026

Identity audit (13)

Slug: nooa-bench-pypi-org
Lifecycle state recorded: 30 Jul 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 30 Jul 2026
Timeline basis: Indexed-at chronology (no inferred launch/funding milestones).
Name from: Written by a language model from the project's public pages.
Category from: Assigned by a language model.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model from page content.
Last updated: 4 Aug 2026
Canonical URL: https://pypi.org/project/nooa-bench

Ship this? Send a correction — no account, and you get a link to follow it.

Also in LLM eval & observability

Same category — not a similarity match