Alternativen zu
A framework for few-shot evaluation of language models.
OpenCompass und Inspect. 2 Alternativen zu LM Evaluation Harness, in Python. Ersatzgrad, Lizenz, Sterne und das neueste signierte Release im Vergleich.
| Tool | Ersatzgrad | Sterne | Lizenz | Bedingungen | Selbst hostbar | Sprache | Neuestes Release | Letzter Push |
|---|---|---|---|---|---|---|---|---|
| OpenCompass | Vollwertiger Ersatz | 7.5k | Apache-2.0 | Open Source | Nein | Python | 0.5.4 | 2026-10-16 |
| Inspect | Teilweise | 3k | MIT | Open Source | Nein | Python | 0.3.281 | 2026-10-17 |
2 Alternativen
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.