A framework for few-shot evaluation of language models.
OpenCompass e Inspect. 2 alternativas a LM Evaluation Harness, em Python. Compare tipo de substituição, licença, estrelas e a última release assinada.
| Ferramenta | Substituição | Estrelas | Licença | Termos | Auto-hospedado | Linguagem | Última release | Último push |
|---|---|---|---|---|---|---|---|---|
| OpenCompass | Substituição completa | 7.5k | Apache-2.0 | Código aberto | Não | Python | 0.5.4 | 2026-10-16 |
| Inspect | Parcial | 3k | MIT | Código aberto | Não | 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.