A framework for few-shot evaluation of language models.
OpenCompass et Inspect. 2 alternatives à LM Evaluation Harness, en Python. Comparez le type de remplacement, la licence, les étoiles et la dernière release signée.
| Outil | Remplacement | Étoiles | Licence | Conditions | Auto-hébergeable | Langage | Dernière release | Dernier push |
|---|---|---|---|---|---|---|---|---|
| OpenCompass | Remplacement complet | 7.5k | Apache-2.0 | Open source | Non | Python | 0.5.4 | 2026-10-16 |
| Inspect | Partiel | 3k | MIT | Open source | Non | Python | 0.3.281 | 2026-10-17 |
2 alternatives
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.