https://guijiagi.com/tags/%E8%AF%84%E6%B5%8B/Recent content in 评测 on 硅基 AGI · 智能体学习与测评Hugozh-cn本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权Thu, 16 Jul 2026 11:25:00 +0800https://guijiagi.com/posts/b1-fc9cb559/Thu, 16 Jul 2026 11:25:00 +0800https://guijiagi.com/posts/b1-fc9cb559/系统梳理大模型评测体系，涵盖知识基准、能力评测、对齐评测与真实场景测试方法论https://guijiagi.com/posts/mistral-large-3-review/Thu, 02 Jul 2026 10:22:00 +0800https://guijiagi.com/posts/mistral-large-3-review/Mistral AI发布Large 3模型，欧洲AI力量正在崛起https://guijiagi.com/posts/rag-evaluation-framework-2026-ragas-custom-metrics/Sun, 28 Jun 2026 10:00:00 +0800https://guijiagi.com/posts/rag-evaluation-framework-2026-ragas-custom-metrics/系统介绍 RAG 系统的评估方法论，涵盖 RAGAS 框架、自定义指标设计和端到端评测流水线https://guijiagi.com/posts/cursor-agent-mode-review/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/cursor-agent-mode-review/Cursor Agent模式评测https://guijiagi.com/posts/gemini-deep-research-eval/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/gemini-deep-research-eval/Gemini Deep Research评测https://guijiagi.com/posts/haystack-framework-review/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/haystack-framework-review/Haystack框架评测https://guijiagi.com/posts/hermes-reasoning-capability/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/hermes-reasoning-capability/Hermes推理能力评测https://guijiagi.com/posts/smolagents-hf-review/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/smolagents-hf-review/HuggingFace smolagents评测https://guijiagi.com/posts/llm-code-gen-eval/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/llm-code-gen-eval/LLM代码生成能力评测https://guijiagi.com/posts/pika-labs-2026/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/pika-labs-2026/Pika Labs 2026新版评测https://guijiagi.com/posts/semantic-kernel-eval/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/semantic-kernel-eval/Semantic Kernel框架评测https://guijiagi.com/posts/windsurf-cascade-deep-review/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/windsurf-cascade-deep-review/Windsurf Cascade深度评测https://guijiagi.com/posts/llm-inference-speed-benchmark/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/llm-inference-speed-benchmark/大模型推理速度评测标准https://guijiagi.com/posts/multimodal-eval-methodology/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/multimodal-eval-methodology/多模态模型评测方法论https://guijiagi.com/posts/kling-video-ai-review/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/kling-video-ai-review/可灵AI视频生成评测https://guijiagi.com/posts/agent-benchmark-2026/Fri, 26 Jun 2026 14:00:00 +0800https://guijiagi.com/posts/agent-benchmark-2026/全面对比 2026 年主流 AI 智能体基准测试框架，分析评估维度差异，探讨智能体评测的方法论与未来方向https://guijiagi.com/posts/llm-judge-evaluation/Fri, 26 Jun 2026 14:00:00 +0800https://guijiagi.com/posts/llm-judge-evaluation/系统介绍 LLM-as-Judge 评估方法的原理、实现与最佳实践，涵盖评分维度设计、Prompt 构建与结果分析https://guijiagi.com/posts/nous-hermes-model-review/Fri, 26 Jun 2026 14:00:00 +0800https://guijiagi.com/posts/nous-hermes-model-review/从推理能力、指令遵循、多语言表现等维度，全面评测 NousResearch Hermes 系列开源大模型。https://guijiagi.com/posts/agent-eval-dataset-construction/Fri, 26 Jun 2026 14:00:00 +0800https://guijiagi.com/posts/agent-eval-dataset-construction/如何为 AGI 智能体构建科学、可复现的评估数据集？从任务设计到标注规范，从偏差控制到动态更新，一份完整的方法论指南。https://guijiagi.com/posts/llm-benchmark-2026-comprehensive/Thu, 25 Jun 2026 10:00:00 +0800https://guijiagi.com/posts/llm-benchmark-2026-comprehensive/盘点 2026 年主流 LLM Benchmark 的有效性、数据污染问题与新趋势