跳到主内容
智客 ZICQ

逻辑推理榜

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。

最近更新:9 分钟前(2026-11-18 10:41)
清除
数据来源与评测方法

声明支持 reasoning 推理 effort 的模型,按 Intelligence 指数排序。

📊 评测基准与方法论说明
1. 数据来源:模型元数据与调用价格每小时自 OpenRouter (openrouter.ai) 官方接口同步,包含商业模型、开源权重及实验预览版本。
2. 评测基准:智能、编码与智能体指数直接源自第三方国际权威评测平台 Artificial Analysis (artificialanalysis.ai) 官方指标。
3. 综合榜权重:综合智能分 = 60% × 综合智力指数 + 25% × 代码生成指数 + 15% × 智能体与工具调用指数。无评测基准数据的模型排在综合榜末尾。
4. 推广链接:标注「推广」的「去调用」按钮是推广链接,ZICQ 可能因此获得佣金;推广关系不影响任何排名与评分。
当前筛选的统计
当前榜单模型数 478
免费可调 17
支持视觉 334
支持工具调用 415
支持推理 361
最长上下文 xAI: Grok 4.20 Multi-Agent 2M tokens
已知输入价格均值 $1.55 / 1M 美元 / 百万 token
最低价模型 Z.ai: GLM 5.2 $0.007 / 1M
当前维度 TOP · 智能指数 Anthropic: Claude Fable 5.2 64.6
⚡ 模型并排 PK 对比器 & Token 成本计算器 点击下方任意模型的「+ PK 对比」即可替换 · 实时测算月度 API 成本 · 支持一键复制对比链接
对比维度 Anthropic: Claude Fable 5.2 Anthropic Anthropic: Claude Fable 5.2 (batch) Anthropic OpenAI: GPT-6.2 Astra OpenAI
综合智能 / 编码 / 智能体 64.6 / 0.0 / 0.0 64.6 / 0.0 / 0.0 62.1 / 0.0 / 0.0
上下文窗口 1M tokens 1M tokens 1.1M tokens
输入 / 输出单价 (1M) $8.00 / $40.00 $4.00 / $20.00 $8.00 / $40.00
预估月度账单 (30天) 输入参数自动测算 输入参数自动测算 输入参数自动测算
  1. #61
    Z.ai: GLM 5.3 Flash Zhipu 智谱 视觉多模态 有基准

    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 27.8
    上下文 1.0M 输出 ≤ 131K
    $0.04/1M $0.08/1M 输出 cache $0.03/1M
    推理能力稳健
  2. #62
    Z.ai: GLM 5.3 Flash (batch) Zhipu 智谱 视觉多模态 有基准

    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 27.8
    上下文 1.0M 输出 ≤ 943K
    $0.02/1M $0.07/1M 输出 cache $0.01/1M
    推理能力稳健
  3. #63
    Xiaomi: MiMo-V2.6-Flash Xiaomi 音视频多模态 有基准

    MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

    工具 视觉 音频 视频 推理 结构化
    智能 26.7
    上下文 1.1M 输出 ≤ 131K
    $0.14/1M $0.28/1M 输出 cache $0.00/1M
    推理能力稳健
  4. #64
    Mistral: Mistral Large 4 Mistral AI 视觉多模态 有基准

    Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

    工具 视觉 推理 结构化
    智能 26.1
    上下文 1.0M 输出 ≤ 262K
    $0.70/1M $2.10/1M 输出 cache $0.07/1M
    推理能力稳健
  5. #65
    Meta: Muse Spark Open Meta 音视频多模态 有基准

    Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...

    工具 视觉 音频 视频 文档 推理 结构化
    智能 24.9
    上下文 1.0M 输出 ≤ 943K
    $1.25/1M $4.25/1M 输出 cache $0.15/1M
    推理能力稳健
  6. #66
    OpenAI: GPT-5.6 Luna OpenAI 文档视觉模型 有基准

    GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

    工具 视觉 文档 推理 结构化
    智能 23.8
    上下文 1.1M 输出 ≤ 128K
    $0.20/1M $1.20/1M 输出 cache $0.02/1M
    推理能力稳健
  7. #67
    OpenAI: GPT-5.6 Luna (batch) OpenAI 文档视觉模型 有基准

    GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

    工具 视觉 文档 推理 结构化
    智能 23.8
    上下文 1.1M 输出 ≤ 128K
    $0.10/1M $0.60/1M 输出 cache $0.01/1M
    推理能力稳健
  8. #68
    DeepSeek: DeepSeek V4 Pro 0813 DeepSeek 通用大语言模型 有基准

    DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

    工具 推理 结构化
    智能 23.1
    上下文 1.0M 输出 ≤ 943K
    $0.11/1M $4.44/1M 输出 cache $0.10/1M
    推理能力稳健
  9. #69
    DeepSeek: DeepSeek V4 Pro 0423 DeepSeek 通用大语言模型 有基准

    DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

    工具 推理 结构化
    智能 20.8
    上下文 1.0M 输出 ≤ 393K
    $0.90/1M $1.50/1M 输出 cache $0.25/1M
    推理能力稳健
  10. #70
    Qwen: Qwen3.8 27B Alibaba 通义 视觉多模态 有基准

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

    工具 视觉 视频 推理 结构化
    智能 20.1
    上下文 1.0M 输出 ≤ 235K
    $0.06/1M $2.20/1M 输出 cache $0.06/1M
    推理能力稳健
  11. #71
    Qwen: Qwen3.8 27B (batch) Alibaba 通义 视觉多模态 有基准

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

    工具 视觉 视频 推理 结构化
    智能 20.1
    上下文 262K 输出 ≤ 235K
    $0.16/1M $2.00/1M 输出 cache $0.04/1M
    推理能力稳健
  12. #72
    MiniMax: MiniMax M3 MiniMax 视觉多模态 有基准

    MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

    工具 视觉 视频 推理 结构化
    智能 18.9
    上下文 1.0M 输出 ≤ 512K
    $0.30/1M $1.20/1M 输出 cache $0.06/1M
    推理能力稳健
  13. #73
    MiniMax: MiniMax M3 (batch) MiniMax 视觉多模态 有基准

    MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

    工具 视觉 视频 推理 结构化
    智能 18.9
    上下文 524K 输出 ≤ 512K
    $0.22/1M $0.88/1M 输出 cache $0.04/1M
    推理能力稳健
  14. #74
    Reflection: Beam 1.0 501B A23B Reflection 通用大语言模型 有基准

    Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...

    工具 推理 结构化
    智能 17.7
    上下文 1.0M 输出 ≤ 943K
    $0.30/1M $1.00/1M 输出 cache $0.04/1M
    推理能力稳健
  15. #75
    MoonshotAI: Kimi K3 Moonshotai 视觉多模态 有基准

    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 17.4
    上下文 1.0M 输出 ≤ 943K
    $0.19/1M $16.00/1M 输出 cache $0.18/1M
    推理能力稳健
  16. #76
    MoonshotAI: Kimi K3 (batch) Moonshotai 视觉多模态 有基准

    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 17.4
    上下文 1.0M 输出 ≤ 16K
    $2.28/1M $11.40/1M 输出 cache $0.23/1M
    推理能力稳健
  17. #77
    Upstage: Solar Pro 4 Upstage 通用大语言模型 有基准

    Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...

    工具 推理 结构化
    智能 14.2
    上下文 524K 输出 ≤ 131K
    $0.15/1M $0.60/1M 输出 cache $0.03/1M
    推理能力稳健
  18. #78
    NVIDIA: Nemotron 3.5 Super VL NVIDIA 视觉多模态 有基准

    NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

    工具 视觉 视频 推理 结构化
    智能 13.6
    上下文 1.0M 输出 ≤ 235K
    $0.15/1M $0.50/1M 输出 cache $0.02/1M
    推理能力稳健
  19. #79
    NVIDIA: Nemotron 3.5 Super VL (free) NVIDIA 视觉多模态 免费 有基准

    NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

    工具 视觉 视频 推理 结构化
    智能 13.6
    上下文 1M 输出 ≤ 131K
    免费
    免费可调 · 限时白嫖
  20. #80
    Thinking Machines: Inkling Small Thinkingmachines 视听多模态 有基准

    Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

    工具 视觉 音频 推理
    智能 12.9
    上下文 524K 输出 ≤ 262K
    $0.45/1M $1.20/1M 输出 cache $0.10/1M
    推理能力稳健