--- title: "lm-evaluation-harness vs just-eval" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/eleutherai-lm-evaluation-harness-vs-re-align-just-eval" tools: ["eleutherai-lm-evaluation-harness", "re-align-just-eval"] --- # lm-evaluation-harness vs just-eval *GraphCanon updated Aug 8, 2026* ## Verdict Pick lm-evaluation-harness if lm-evaluation-harness is a Python framework for evaluating language models in various parallelism modes using different checkpoint formats, compatible with the Megatron-LM backend; pick just-eval if just-eval provides a straightforward GPT-based framework for evaluating LLMs across multiple dimensions with clear outputs. [lm-evaluation-harness](https://www.eleuther.ai) reports 14k GitHub stars, 3.5k forks, and 938 open issues, last pushed Jul 13, 2026. [just-eval](https://allenai.github.io/re-align/) has 90 stars, 7 forks, and 2 open issues, last pushed Jan 29, 2024. Figures are from public GitHub metadata via [lm-evaluation-harness's repository](https://github.com/EleutherAI/lm-evaluation-harness) and [just-eval's repository](https://github.com/Re-Align/just-eval). | | [lm-evaluation-harness](/tools/eleutherai-lm-evaluation-harness.md) | [just-eval](/tools/re-align-just-eval.md) | | --- | --- | --- | | Tagline | A framework for few-shot evaluation of language models. | A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs. | | Stars | 13,560 | 90 | | Forks | 3,467 | 7 | | Open issues | 938 | 2 | | Language | Python | Python | | Adopt for | lm-evaluation-harness is a Python framework for evaluating language models in various parallelism modes using different checkpoint formats, compatible with the Megatron-LM backend. | just-eval provides a straightforward GPT-based framework for evaluating LLMs across multiple dimensions with clear outputs. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | Evaluation & Observability | Evaluation & Observability | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [lm-evaluation-harness](/tools/eleutherai-lm-evaluation-harness.md) | [just-eval](/tools/re-align-just-eval.md) | | --- | --- | --- | | Maintenance | Active (82%) | Dormant (18%) | | Days since push | 24d | 921d | | Open issues (now) | 938 | 2 | | Full report | [trust report](/tools/eleutherai-lm-evaluation-harness/trust.md) | [trust report](/tools/re-align-just-eval/trust.md) | ## Shared compatibility - **Python**: [lm-evaluation-harness](/tools/eleutherai-lm-evaluation-harness.md) - Python runtime; [just-eval](/tools/re-align-just-eval.md) - Python runtime ## Decision facts: lm-evaluation-harness - **Adopt for:** lm-evaluation-harness is a Python framework for evaluating language models in various parallelism modes using different checkpoint formats, compatible with the Megatron-LM backend. ## Decision facts: just-eval - **Adopt for:** just-eval provides a straightforward GPT-based framework for evaluating LLMs across multiple dimensions with clear outputs. ## Choose when ### Choose lm-evaluation-harness if… - Tags unique to lm-evaluation-harness: data-parallelism, evaluation-framework, expert-parallelism, language-model. - - When you need to evaluate large language models across multiple GPUs in data or tensor parallel configurations. - More GitHub stars (14k vs 90) - visibility, not fit. ### Choose just-eval if… - Tags unique to just-eval: evaluation, gpt4, llm, llm-eval. - When your team requires an in-depth yet interpretable evaluation of LLM performance, focusing on various aspects. - Leaner open-issue backlog (2). ## When NOT to use lm-evaluation-harness - - If your evaluation setup requires pipeline parallelism not currently supported by this framework. ## When NOT to use just-eval - Avoid if direct integration with competing API services is needed as just-eval focuses solely on OpenAI API key configuration. - Not suitable when your project demands a custom evaluation framework that extends beyond simple GPT-based assessments. ## Common questions ### What is the difference between lm-evaluation-harness and just-eval? lm-evaluation-harness: A framework for few-shot evaluation of language models.. just-eval: A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.. See the comparison table for live GitHub stats and shared categories. ### When should I choose lm-evaluation-harness over just-eval? Choose lm-evaluation-harness over just-eval when Tags unique to lm-evaluation-harness: data-parallelism, evaluation-framework, expert-parallelism, language-model; - When you need to evaluate large language models across multiple GPUs in data or tensor parallel configurations; More GitHub stars (14k vs 90) - visibility, not fit. ### When should I choose just-eval over lm-evaluation-harness? Choose just-eval over lm-evaluation-harness when Tags unique to just-eval: evaluation, gpt4, llm, llm-eval; When your team requires an in-depth yet interpretable evaluation of LLM performance, focusing on various aspects; Leaner open-issue backlog (2). ### When should I avoid lm-evaluation-harness? - If your evaluation setup requires pipeline parallelism not currently supported by this framework. ### When should I avoid just-eval? Avoid if direct integration with competing API services is needed as just-eval focuses solely on OpenAI API key configuration. Not suitable when your project demands a custom evaluation framework that extends beyond simple GPT-based assessments. ### Is lm-evaluation-harness or just-eval more popular on GitHub? lm-evaluation-harness has more GitHub stars (13,560 vs 90). Stars measure visibility, not whether either tool fits your constraints. ### Are lm-evaluation-harness and just-eval open source? Yes - both are open-source projects on GitHub (lm-evaluation-harness: MIT, just-eval: MIT). ### Where can I find alternatives to lm-evaluation-harness or just-eval? GraphCanon lists graph-backed alternatives at [lm-evaluation-harness alternatives](/tools/eleutherai-lm-evaluation-harness/alternatives) and [just-eval alternatives](/tools/re-align-just-eval/alternatives) ([lm-evaluation-harness markdown twin](/tools/eleutherai-lm-evaluation-harness/alternatives.md), [just-eval markdown twin](/tools/re-align-just-eval/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/eleutherai-lm-evaluation-harness-vs-re-align-just-eval.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, lm-evaluation-harness or just-eval? lm-evaluation-harness: Active. just-eval: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for lm-evaluation-harness and just-eval? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [lm-evaluation-harness trust report](/tools/eleutherai-lm-evaluation-harness/trust); [just-eval trust report](/tools/re-align-just-eval/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=eleutherai-lm-evaluation-harness`](/api/graphcanon/graph?tool=eleutherai-lm-evaluation-harness) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_