AgentBench vs OpenCompass

AgentBench has no write-up on Specifiction yet; its figures are above.

OpenCompass is a free, open-source Python platform for evaluating large language models across knowledge, reasoning, coding, science, language, long-context and safety datasets. It describes support for models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek and other providers, along with more than 100 datasets. Evaluations can use zero-shot, few-shot or chain-of-thought methods with standard or dialogue prompt templates. The system supports task division, distributed evaluation and data-parallel work across multiple GPUs. Configuration files record experiments, and results can be reported in real time. Its modular design can be extended with models, datasets, task-division strategies and cluster-management systems. OpenCompass evaluates API models as well as open-source models; installation documentation lists LMDeploy and vLLM inference backends and an API option. A VLMEvalKit integration supports multimodal dataset loading, OpenAI-compatible inference and VLMEvalKit metrics. It is intended for self-hosted use under the Apache-2.0 license. The README recommends Python 3.12, while pyext-backed code-evaluation datasets require Python 3.10. Some datasets and agent evaluations need extra dependencies that may conflict.