LM Evaluation Harness
An open-source framework for evaluating and benchmarking language models
- Vendor
- EleutherAI
- Also known as
- lm-evaluation-harness
What is LM Evaluation Harness?
A framework for conducting few-shot evaluation of language models against various tasks and benchmarks. Supports multiple model backends, custom evaluation metrics, and extensible task definitions for assessing model capabilities and performance.
LM Evaluation Harness pricing
We don't have LM Evaluation Harness's full plan breakdown yet (its pricing page resisted automated reading). Here's what we could confirm. Always check live pricing for exact numbers.
What LM Evaluation Harness does
The capabilities that matter for ai evals testing, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.
- Architecture model
- Open source CLI
- LLM as a judge prompt grading framework
- -
- Specialized rag metrics faithfulness context relevance
- -
- Deterministic regex and json schema assertions
- -
- Synthetic test dataset generation from documents
- -
- Ci cd github actions pipeline blocking gates
- -
- Red teaming and adversarial vulnerability scanning
- -
- Multi model side by side ab regression testing
- ✓
- Human in the loop hitl annotation UI
- -
- Dashboard analytics for metric drift over time
- -
- SOC2 type ii
- -
- Mit or apache permissive oss license
- -
- Pricing model
- Free open source
Platform & deployment
Independently observed- CLI
- macOS
- Linux
- Windows
- Self-hosted
Integrations (5)
Independently observed- Hugging Face
- PyTorch
- VLLM
- GitHub
- OpenAI-compliant APIs
Security & compliance
Known vulnerabilities: 0 (0 in the last 12 months) sourcea count reflects scale & disclosure, not quality
LM Evaluation Harness FAQ
Common questions about LM Evaluation Harness, answered from independent, dated evidence.
What is LM Evaluation Harness?
A Python-based evaluation framework that enables testing of language models against 60+ standard academic benchmarks with support for various model formats, APIs, and custom evaluation metrics. It is indexed under AI Evals Testing.
Source: https://github.com/pricing
Is LM Evaluation Harness free to use?
LM Evaluation Harness is open source, so it can be self-hosted and used at no licence cost. It is released under the MIT licence. Pricing changes often, so verify at source before relying on it.
Source: https://github.com/pricing
What platforms does LM Evaluation Harness support?
LM Evaluation Harness supports a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.
Source: https://github.com/pricing
Can LM Evaluation Harness be self-hosted?
Yes. LM Evaluation Harness can be deployed self-hosted, so it does not have to run on the vendor's infrastructure.
Source: https://github.com/pricing
What does LM Evaluation Harness integrate with?
We have confirmed 5 integrations for LM Evaluation Harness, including Hugging Face, PyTorch, VLLM, GitHub and OpenAI-compliant APIs. This is what we could verify from public sources, so the vendor may support others we have not indexed.
Source: https://github.com/pricing
Is LM Evaluation Harness open source?
Yes. LM Evaluation Harness is published under the MIT licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.
LM Evaluation Harness alternatives
Other ai evals testing we track, ranked by the same independent score.
- Patronus AIAutomated evaluation and monitoring platform for testing and optimizing language models and AI agentslow · 30%
- TruLensA library for tracking and evaluating LLM applications to identify failure points and cost-saving opportunities.low · 29%
- GalileoAI evaluation and observability platform for testing, monitoring, and improving AI systemslow · 7%
- OpenAI EvalsFramework for evaluating and benchmarking large language models and LLM-based systemslow · 22%
Compare LM Evaluation Harness
Side by side against other ai evals testing, attribute by attribute, with a source on every value.
The vioscaleAI score: one lens on the evidence
Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for LM Evaluation Harness, not the verdict.
| Signal | Score | Weight | Contribution | Evidence |
|---|---|---|---|---|
| Development activity | 56 | 0.12 | 6.7 | ✓ |
| Release cadence | 60 | 0.07 | 4.0 | ✓ |
| Dependent projects | 40 | 0.08 | 3.2 | ✓ |
| Security score | 55 | 0.05 | 2.9 | ✓ |
| Stars | 78 | 0.03 | 2.6 | ✓ |
| Capabilities | 29 | 0.08 | 2.4 | ✓ |
| Integrations | 22 | 0.05 | 1.2 | ✓ |
| Security posture | 0 | 0.09 | 0.0 | - |
| Package downloads | 0 | 0.17 | 0.0 | - |
| Developer Q&A activity | 0 | 0.08 | 0.0 | - |
Computed . Re-weight it by intent, or see the full method.
All data & sourcesshow ↓
Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.
Activity
| Attribute | Value | Evidence |
|---|---|---|
| Commits last 30d | 57 | mediumsource · 2026-09-14 · 65% |
Adoption
Content
| Attribute | Value | Evidence |
|---|---|---|
| Faq | 6 items | mediumsource · 2026-09-10 · 66% |
Features
| Attribute | Value | Evidence |
|---|---|---|
| Capabilities | Pricing model: free_open_source · Architecture model: open_source_cli · Multi model side by side ab regression testing: Yes | mediumsource · 2026-10-14 · 60% |
Integrations
| Attribute | Value | Evidence |
|---|---|---|
| Count | 5 | mediumsource · 2026-08-21 · 60% |
Language
| Attribute | Value | Evidence |
|---|---|---|
| Primary | Python | highsource · 2026-10-14 · 90% |
License
| Attribute | Value | Evidence |
|---|---|---|
| Spdx | MIT | highsource · 2026-10-14 · 95% |
Pricing
Release
Security
| Attribute | Value | Evidence |
|---|---|---|
| Scorecard | 5.5 | highsource · 2026-10-14 · 90% |
| Vulnerabilities | Count: 0 · Source: https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=lm-eval&per_page=100 · Last 12m: 0 | highsource · 2026-10-14 · 90% |
| Trust center | https://github.com/security | mediumsource · 2026-10-14 · 60% |
Is LM Evaluation Harness the right choice for you?
Tell us the job, the constraints and what you weigh most, and we will rank LM Evaluation Harness against the rest of the ai evals testing we index, using the same dated evidence weighted your way.
Free to run, no account needed to start. How the evaluation works
Is this your product?
This profile was built from public sources without asking you. You can take the badge below and use it anywhere, and you can claim the profile to correct anything we got wrong. Both are free, and neither moves LM Evaluation Harness up or down: nobody can buy rank here, including you.
Take the badge
Live, always current, and free to use on your own site. It shows LM Evaluation Harness's independent score and links back to this profile.
<a href="https://www.vioscale.ai/software/lm-evaluation-harness" target="_blank" rel="noopener">
<img src="https://www.vioscale.ai/badge/software/lm-evaluation-harness.svg" alt="LM Evaluation Harness, verified on vioscaleAI" width="330" height="76" loading="lazy" />
</a>Markdown, for a README →
[](https://www.vioscale.ai/software/lm-evaluation-harness)Claim the profile
Verify you control the domain, then point us at the pages that state the facts about LM Evaluation Harness and add your own description and media. Free, and it does not change the score.
- Correct anything wrong, with evidence
- Point our crawler at the pages that matter
- Write your own description and add media
Not the owner? How vendor profiles work