LM Evaluation Harness

Open source

Open source framework for benchmarking language models across standardized tasks.

by EleutherAIOfficial site ↗Source code ↗

Pricing: free
Free tier: true
License: open-source
Open source: Yes

Editorial review

LM Evaluation Harness has not yet been editorially reviewed. User reviews and published field data below are unaffected — we say so rather than implying an editorial verdict.

Facts & attributes

Every value carries its evidence state. “—” means unknown — never a silent default (P-02).

Identity · Taxonomy

Tags(open-source;cloud-native): open-source, evaluation, llm, benchmarkingVerification pending

Platform · Deployment

Delivery model(SaaS;self-hosted;desktop;mobile;embedded;managed-cloud;appliance): self-hostedVerified

Pricing · Licensing

Free plan(true/false): trueVerification pending
License model(proprietary;open-source;source-available;dual-license): open-sourceVerification pending
Pricing model(free;subscription;usage;seat;asset;transaction;revenue-share;perpetual;custom): freeVerified
Source repository(HTTPS URL): https://github.com/EleutherAI/lm-evaluation-harnessVerified
SPDX license IDs(Apache-2.0;MIT): MITVerified

Features · Product · Fit

Core capabilities(authoring;automation;analytics): few-shot evaluation of language models, YAML-configured task creation, vLLM and SGLang model support, plugin system for custom backends, multimodal task prototypingVerification pending

Api · Integrations · Ecosystem

API available(true/false): trueVerification pending
CLI(true/false): trueVerification pending

Audience · Use · Case

Best for(Neutral editorial summary): Open-source MIT framework from EleutherAI for few-shot evaluation of language models with YAML-configured tasks and a CLI.Verification pending
Primary use cases(build;monitor;automate): language model benchmarking, open LLM leaderboard tasks, model evaluation researchVerification pending

Lifecycle · Versioning

Current version(1.12.3): v0.4.13Verified
Maintenance status(active;maintenance;deprecated;EOL;archived): activeVerification pending

Vendor · Maintainer

Founded year(2012): 2020Verified
Vendor type(commercial;foundation;community;government;consortium;individual): communityVerified

User reviews

Review policy

No published reviews yet.