evalscope/docs/en/advanced_guides/custom_model.md

Custom Model

LLM Model Evaluation

Evaluation of large language models currently supports two methods: Native Evaluation and OpenCompass Evaluation.

Method 1: Using Native Evaluation

See [Basic Usage Guide](../get_started/basic_usage.md)

Method 2: Using OpenCompass Evaluation

See [OpenCompass Usage Guide](../user_guides/backend/opencompass_backend.md)

---

VLM Model Evaluation

Currently, evaluation of multimodal models only supports the VLMEvalKit backend.

Using VLMEvalKit Backend

See [VLMEvalKit Usage Guide](../user_guides/backend/vlmevalkit_backend.md)