综合大模型榜
智客 ZICQ 大模型榜单每日更新，覆盖智能、编程、价格与上下文，便于选型与比价。
依据 OpenRouter benchmarks 智能指数 / 编码 / 智能体加权综合排序（60% / 25% / 15%），覆盖全部 338+ 个模型。
最近更新：15 分钟前（2026-10-04 16:36）-
#1
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...
工具 视觉 文档 推理 结构化智能 53.4编码 81.6智能体 57.9上下文 1M 输出 ≤ 128K$10.00/1M $50.00/1M 输出 cache $0.25/1MTOP 领跑旗舰 -
#2
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...
工具 视觉 文档 推理 结构化智能 53.4编码 81.6智能体 57.9上下文 1M 输出 ≤ 128K$5.00/1M $25.00/1M 输出 cache $0.12/1M综合实力前三 -
#3
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
工具 视觉 文档 推理 结构化智能 52.7编码 76.9智能体 51.0上下文 1.1M 输出 ≤ 128K$10.00/1M $50.00/1M 输出 cache $1.00/1M综合实力前三 -
#4
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
工具 视觉 文档 推理 结构化智能 52.7编码 76.9智能体 51.0上下文 1.1M 输出 ≤ 128K$5.00/1M $25.00/1M 输出 cache $0.50/1M百万上下文极客首选 -
#5
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
工具 视觉 文档 推理 结构化智能 50.8编码 78.0智能体 56.5上下文 1M 输出 ≤ 128K$5.00/1M $25.00/1M 输出 cache $0.50/1M百万上下文极客首选 -
#6
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
工具 视觉 文档 推理 结构化智能 50.8编码 78.0智能体 56.5上下文 1M 输出 ≤ 128K$2.50/1M $12.50/1M 输出 cache $0.25/1M百万上下文极客首选 -
#7
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
工具 视觉 文档 推理 结构化智能 49.6编码 76.5智能体 50.7上下文 1M 输出 ≤ 128K$10.00/1M $50.00/1M 输出 cache $1.00/1M百万上下文极客首选 -
#8
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
工具 视觉 文档 推理 结构化智能 49.6编码 76.5智能体 50.7上下文 1M 输出 ≤ 128K$5.00/1M $25.00/1M 输出 cache $0.50/1M百万上下文极客首选 -
#9
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
工具 视觉 文档 推理 结构化智能 47.0编码 77.4智能体 50.2上下文 1.1M 输出 ≤ 128K$2.00/1M $10.00/1M 输出 cache $0.20/1M百万上下文极客首选 -
#10
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
工具 视觉 文档 推理 结构化智能 47.0编码 77.4智能体 50.2上下文 1.1M 输出 ≤ 128K$1.00/1M $5.00/1M 输出 cache $0.10/1M百万上下文极客首选 -
#11
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...
工具 视觉 视频 推理 结构化智能 45.4编码 76.2智能体 56.0上下文 1M 输出 ≤ 131K$2.00/1M $6.00/1M 输出 cache $0.25/1M百万上下文极客首选 -
#12
Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).
工具 视觉 文档 推理 结构化智能 44.3编码 76.8智能体 53.0上下文 500K 输出 ≤ 450K$2.00/1M $6.00/1M 输出 cache $0.50/1M推荐实时模型 -
#13
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
工具 推理 结构化智能 44.8编码 74.8智能体 53.1上下文 1.0M 输出 ≤ 131K$1.40/1M $4.40/1M 输出 cache $0.14/1M百万上下文极客首选 -
#14
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
工具 推理 结构化智能 44.8编码 74.8智能体 53.1上下文 1.0M 输出 ≤ 131K$0.45/1M $2.00/1M 输出 cache $0.10/1M百万上下文极客首选 -
#15
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
工具 视觉 视频 推理 结构化智能 43.6编码 76.2智能体 50.0上下文 1.0M 输出 ≤ 943K$0.72/1M $13.00/1M 输出 cache $0.70/1M百万上下文极客首选 -
#16
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
工具 视觉 视频 推理 结构化智能 43.6编码 76.2智能体 50.0上下文 1.0M 输出 ≤ 16K$2.28/1M $11.40/1M 输出 cache $0.23/1M百万上下文极客首选 -
#17
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
工具 视觉 文档 推理 结构化智能 42.1编码 76.7智能体 43.2上下文 1.1M 输出 ≤ 128K$2.00/1M $12.00/1M 输出 cache $0.20/1M百万上下文极客首选 -
#18
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
工具 视觉 文档 推理 结构化智能 42.1编码 76.7智能体 43.2上下文 1.1M 输出 ≤ 128K$1.00/1M $6.00/1M 输出 cache $0.10/1M百万上下文极客首选 -
#19
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
工具 视觉 视频 推理 结构化智能 41.8编码 71.5智能体 50.9上下文 1.0M 输出 ≤ 943K$0.15/1M $0.50/1M 输出 cache $0.03/1M百万上下文极客首选 -
#20
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
工具 视觉 视频 推理 结构化智能 41.8编码 71.5智能体 50.9上下文 1.0M 输出 ≤ 131K$0.06/1M $0.20/1M 输出 cache $0.01/1M百万上下文极客首选