Galileo vs LM Evaluation Harness
Galileo
galileo.aiLM Evaluation Harness
github.comSide by side
| Figure | Galileo | LM Evaluation Harness |
|---|---|---|
| Price from | $100/mo | Free |
| Free plan | — | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | — |
| Linux | — | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 3 | 1 |
| Spec score · LLM Evaluation Tools | 7.8 (#11) | 7.5 (#17) |
| Spec score · AI LLM Evaluation Tools | 7.9 (#17) | 7.6 (#21) |
| Purpose | Galileo is an observability, evaluation, and guardrail platform for GenAI and agentic applications. | LM Evaluation Harness is a unified framework for evaluating generative language models across evaluation tasks. |
| Support | The Pro plan includes dedicated Slack support, and Enterprise includes 24/7 support via Slack, email, or phone. | The project directs users to open a GitHub issue or join the EleutherAI Discord for support. |
Plans
In their own words
Galileo
Galileo is an observability, evaluation and guardrail platform for generative AI and agentic applications. It provides ready-made evaluations for RAG, agents, safety and security, as well as custom evaluators. Observability tools analyze agent behavior to surface patterns and failure modes, while Galileo Experiments let teams evaluate datasets and prompts systematically and compare results. Evaluation scores can guide agent actions, tool access and escalation paths. Developers can use Python and TypeScript SDKs or the API, with integrations including CrewAI, Google ADK, LangChain and LangGraph, OpenAI, Microsoft Agent Framework, Strands Agents and Vercel AI SDK. Deployment options include SaaS, virtual private cloud and on-premises. The Free plan includes 5,000 traces per month, unlimited users and unlimited custom evaluations. Pro costs $100 a month, billed yearly, and includes 50,000 traces per month; pricing scales with trace volume. SSO supports OIDC and SAML only on a customer's own Galileo cluster, not the free version or hosted app.galileo.ai service.
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.