alternatif untuk
A framework for few-shot evaluation of language models.
OpenCompass dan Inspect. 2 alternatif LM Evaluation Harness, dalam Python. Bandingkan kecocokan, lisensi, bintang, dan rilis bertanda tangan terbaru.
| Alat | Kecocokan | Bintang | Lisensi | Ketentuan | Self-hosted | Bahasa | Terbaru | Push terakhir |
|---|---|---|---|---|---|---|---|---|
| OpenCompass | Pengganti penuh | 7.5k | Apache-2.0 | Open source | Tidak | Python | 0.5.4 | 2026-10-16 |
| Inspect | Sebagian | 3k | MIT | Open source | Tidak | Python | 0.3.281 | 2026-10-17 |
2 alternatif
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.