A framework for few-shot evaluation of language models.
OpenCompass e Inspect. 2 alternativas a LM Evaluation Harness, en Python. Compara el nivel de sustitución, la licencia, las estrellas y la última versión firmada.
| Herramienta | Sustitución | Estrellas | Licencia | Condiciones | Autoalojable | Lenguaje | Última versión | Último push |
|---|---|---|---|---|---|---|---|---|
| OpenCompass | Sustitución completa | 7.5k | Apache-2.0 | Código abierto | No | Python | 0.5.4 | 2026-10-16 |
| Inspect | Parcial | 3k | MIT | Código abierto | No | Python | 0.3.281 | 2026-10-17 |
2 alternativas
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
Runs benchmark suites over local and API models from a config.
Inspect: A framework for large language model evaluations
Runs benchmark tasks, but is built around custom evals and agents.