LM Evaluation Harness vs Promptfoo
LM Evaluation Harness
github.comPromptfoo
promptfoo.devSide by side
| Figure | LM Evaluation Harness | Promptfoo |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | Yes |
| Web | — | Yes |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 3 |
| Spec score · LLM Evaluation Tools | 7.5 (#17) | 8.4 (#6) |
| Spec score · AI LLM Evaluation Tools | 7.6 (#21) | 8.4 (#13) |
| Installation | The base package provides the core framework while model backends are installed separately as optional extras. | Installation is available through npm, npx, Homebrew, and a project dependency; npm and npx require Node.js 22.22.0 or newer. |
| Support | The project directs users to open a GitHub issue or join the EleutherAI Discord for support. | Community support is provided through chat and GitHub issues, while Enterprise includes professional services and dedicated Slack support. |
Plans
In their own words
LM Evaluation Harness
LM Evaluation Harness is a free, open-source framework for evaluating generative language models across many tasks. It lists more than 60 standard academic benchmarks, with hundreds of subtasks and variants. Supported model options include Hugging Face Transformers, GPT-NeoX, Megatron-DeepSpeed, and vLLM. The harness also connects to hosted OpenAI and Anthropic APIs and to local servers compatible with OpenAI APIs. Users can define prompts and metrics, configure tasks with YAML, and extend model backends, filters, metrics, and aggregations through external packages or local modules. Publicly available prompts are intended to support reproducibility and comparison between papers. The base package contains the core framework; model backends are separate optional installs. It runs self-hosted on Linux and API environments, with documented Windows ML and ONNX Runtime accelerator options. MIT licensing applies. APIs without logits or log probabilities are limited to generate-until tasks.
Promptfoo
Promptfoo helps developers and enterprises evaluate prompts and test AI applications for security risks. It compares prompt outputs across multiple models in a web view. Red-team testing simulates users to look for prompt injections, jailbreaks, data leaks, business rule violations and insecure agent tool use. Its getting-started guide lists more than 60 providers, including OpenAI, Anthropic, Google and local models such as Ollama. Integrations include CI systems such as GitHub Actions, GitLab CI, Jenkins, Azure Pipelines, CircleCI and Bitbucket Pipelines, plus Splunk, Burp Suite, Google Sheets and MCP. Installation is available through npm, npx or Homebrew. Promptfoo requires Node.js 22.22.0 or newer and recommends Node.js 24 LTS. The free Community plan includes all LLM evaluation features and 10k red-team probes per month, and can run locally or be self-hosted. Enterprise includes managed cloud deployment; On-Premise runs on customer infrastructure. Promptfoo says it is based in San Francisco, is now part of OpenAI and remains open source.