Project Knowledge

EleutherAI/lm-evaluation-harness

Use EleutherAI/lm-evaluation-harness when the user needs a llm eval project with docker, library-only, local deployment options.

TypeProject / implementation

Difficultyintermediate

LanguagePython

LicenseMIT

TL;DR

Use EleutherAI/lm-evaluation-harness when the user needs a llm eval project with docker, library-only, local deployment options.

Install

Run with Docker using the repository's container instructions.

Good For

evaluate LLM outputs

benchmark prompts and agents

track model quality

Not Good For

edge-only Cloudflare Workers deployment without adaptation

users expecting a complete hosted product

production inference serving

Git.Top Score86/100

Agent Score80/100

Maintenance55

Stability76

Quality35/100

Best Use

evaluate LLM outputs

Primary situation where this project is a good shortlist candidate.

Watch Out

edge-only Cloudflare Workers deployment without adaptation

Main reason to compare alternatives before adopting it.

Deployment Fit

docker, library_only, local

Git.Top did not classify this as Cloudflare-ready. Evidence: Runtime blocker: python, cuda, gpu.

Best Alternative

comet-ml/opik: docker, kubernetes

Compare this option when the target stack or language preference differs.

Confidence

3/4 classification signals high; 3 quality signals complete or snapshot

Classification evidence and quality signal confidence should be checked before production recommendations.

Freshness

Repo 2026-09-20; metrics 2026-09-20

Repository and metric timestamps for this knowledge record.

Freshness

Repository and metrics timestamps

Repository synced2026-09-20T21:01:02.778Z

Metrics calculated2026-09-20T21:01:02.778Z

Scoring

Quality and agent score are separate

Quality score weights star movement, commits, releases, contributors, and issue response. Agent score weights documentation, maintenance, deployment, popularity, and community.

Confidence

Signal confidence

Stars 30dsnapshot

Commits 30dcomplete

Releases 180dcomplete

Contributors 90dpartial

Badge

Agent Score badge

Embed a lightweight SVG badge for this repository.

Project Type

Project / implementation

This repository is treated as an implementation project. Compare its deployment fit, maintenance, and alternatives before adopting it.

Cloudflare Readiness

No Cloudflare-ready signal

Git.Top did not classify this as Cloudflare-ready. Evidence: Runtime blocker: python, cuda, gpu.

Selection Guidance

Use the evidence before choosing

Treat this page as a shortlist input. Confirm source metadata, classification confidence, deployment evidence, and current repository activity before making a production recommendation.

Alternatives

Comparable projects

JSON

comet-ml/opikUse comet-ml/opik when the user needs a llm eval project with docker, kubernetes, library-only deployment options.

confident-ai/deepevalUse confident-ai/deepeval when the user needs a llm eval project with library-only, local, cloud deployment options.

GoogleCloudPlatform/evalbenchUse GoogleCloudPlatform/evalbench when the user needs a llm eval project with docker, local, cloud deployment options.

Arize-ai/phoenixUse Arize-ai/phoenix when the user needs a llm eval project with docker, vercel, serverless deployment options.

modelscope/evalscopeUse modelscope/evalscope when the user needs a llm eval project with docker, library-only, local deployment options.

Related Projects

Adjacent ecosystem projects

JSON

promptfoo/promptfooUse promptfoo/promptfoo when the user needs a llm eval project with docker, library-only, local deployment options. Shared llm eval category and docker deployment context.

ai-twinkle/EvalUse ai-twinkle/Eval when the user needs a llm eval project with docker, library-only, local deployment options. Shared llm eval category and docker deployment context.

modelscope/evalscopeUse modelscope/evalscope when the user needs a llm eval project with docker, library-only, local deployment options. Shared llm eval category and docker deployment context.

agentevals-dev/agentevalsUse agentevals-dev/agentevals when the user needs a llm eval project with docker, kubernetes, library-only deployment options. Shared llm eval category and docker deployment context.

vibrantlabsai/ragasUse vibrantlabsai/ragas when the user needs a llm eval project with docker, library-only, local deployment options. Shared llm eval category and docker deployment context.

ianarawjo/ChainForgeUse ianarawjo/ChainForge when the user needs a llm eval project with docker, library-only, local deployment options. Shared llm eval category and docker deployment context.

Deploy

Supported deployment paths

Compatible With

Inferred dependencies and protocols

Use Cases

Where agents should consider it

Classification Evidence

Why Git.Top categorized this project

Full JSON

Category: highMatched "eval" in metadata. Matched "evaluation" in metadata.

Deployment: highMatched "pip install" in repository content. Matched "library" in repository content.

Difficulty: mediumNo strong beginner or advanced signal found; defaulting to intermediate.

Cloudflare Ready: highRuntime blocker: python, cuda, gpu. No Cloudflare deployment signal detected.

Compare

comet-ml/opik leads this context

JSON

ProjectStarsAgentLocalCloudflareScore

EleutherAI/lm-evaluation-harness14,036NoYesNo80

comet-ml/opik22,171NoYesNo90

confident-ai/deepeval18,355NoYesNo84

GoogleCloudPlatform/evalbench57NoYesNo70