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:52 分钟前(2026-11-21 04:34)
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 476
免费可调 15
支持视觉 335
支持工具调用 414
支持推理 359
最长上下文 SpaceXSI: Grok 4.20 Multi-Agent 2M tokens
已知输入价格均值 $1.57 / 1M 美元 / 百万 token
最低价模型 inclusionAI: Ling 3.0 Tiny $0.015 / 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. #281
    Anthropic: Claude Sonnet 4.6 (batch) Anthropic 文档视觉模型

    Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $1.50/1M $7.50/1M 输出 cache $0.15/1M
    推理能力稳健
  2. #282
    Qwen: Qwen3.5 Plus 2026-02-15 Alibaba 通义 视觉多模态

    The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

    工具 视觉 视频 推理 结构化
    上下文 1M 输出 ≤ 65K
    $0.26/1M $1.56/1M 输出
    推理能力稳健
  3. #283
    Qwen: Qwen3.5 397B A17B Alibaba 通义 视觉多模态

    The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

    工具 视觉 视频 推理 结构化
    上下文 262K 输出 ≤ 81K
    $0.45/1M $3.00/1M 输出 cache $0.22/1M
    推理能力稳健
  4. #284
    MiniMax: MiniMax M2.5 MiniMax 通用大语言模型

    MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

    工具 推理 结构化
    上下文 198K 输出 ≤ 176K
    $0.29/1M $1.20/1M 输出 cache $0.06/1M
    推理能力稳健
  5. #285
    Z.ai: GLM 5 Zhipu 智谱 通用大语言模型

    GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

    工具 推理 结构化
    上下文 204K 输出 ≤ 131K
    $1.00/1M $3.20/1M 输出 cache $0.20/1M
    推理能力稳健
  6. #286
    Anthropic: Claude Opus 4.6 Anthropic 文档视觉模型

    Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $5.00/1M $25.00/1M 输出 cache $0.50/1M
    推理能力稳健
  7. #287
    Anthropic: Claude Opus 4.6 (batch) Anthropic 文档视觉模型

    Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

    工具 视觉 文档 推理 结构化
    上下文 1M 输出 ≤ 128K
    $2.50/1M $12.50/1M 输出 cache $0.25/1M
    推理能力稳健
  8. #288
    MoonshotAI: Kimi K2.5 Moonshotai 视觉多模态

    Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

    工具 视觉 推理 结构化
    上下文 262K 输出 ≤ 235K
    $0.50/1M $2.50/1M 输出 cache $0.15/1M
    推理能力稳健
  9. #289
    Z.ai: GLM 4.7 Flash Zhipu 智谱 通用大语言模型

    As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...

    工具 推理 结构化
    上下文 200K 输出 ≤ 117K
    $0.06/1M $0.40/1M 输出
    推理能力稳健
  10. #290
    OpenAI: GPT-5.2-Codex OpenAI 视觉多模态

    GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

    工具 视觉 推理 结构化
    上下文 400K 输出 ≤ 128K
    $1.75/1M $14.00/1M 输出 cache $0.17/1M
    推理能力稳健
  11. #291
    Z.ai: GLM 4.7 Zhipu 智谱 通用大语言模型

    GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

    工具 推理 结构化
    上下文 204K 输出 ≤ 131K
    $0.40/1M $1.75/1M 输出 cache $0.08/1M
    推理能力稳健
  12. #292
    Google: Gemini 3 Flash Preview Google DeepMind 音视频多模态

    Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

    工具 视觉 音频 视频 文档 推理 结构化
    上下文 1.0M 输出 ≤ 65K
    $0.50/1M $3.00/1M 输出 cache $0.05/1M
    推理能力稳健
  13. #293
    Google: Gemini 3 Flash Preview (batch) Google DeepMind 音视频多模态

    Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

    工具 视觉 音频 视频 文档 推理 结构化
    上下文 1.0M 输出 ≤ 65K
    $0.25/1M $1.50/1M 输出
    推理能力稳健
  14. #294
    NVIDIA: Nemotron 3 Nano 30B A3B NVIDIA 通用大语言模型

    NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

    工具 推理 结构化
    上下文 262K 输出 ≤ 235K
    $0.06/1M $0.24/1M 输出 cache $0.01/1M
    推理能力稳健
  15. #295
    OpenAI: GPT-5.2 Pro OpenAI 文档视觉模型

    GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...

    工具 视觉 文档 推理 结构化
    上下文 400K 输出 ≤ 128K
    $21.00/1M $168.00/1M 输出
    推理能力稳健
  16. #296
    OpenAI: GPT-5.2 Pro (batch) OpenAI 文档视觉模型

    GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...

    工具 视觉 文档 推理 结构化
    上下文 400K 输出 ≤ 128K
    $10.50/1M $84.00/1M 输出
    推理能力稳健
  17. #297
    OpenAI: GPT-5.2 OpenAI 文档视觉模型

    GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

    工具 视觉 文档 推理 结构化
    上下文 400K 输出 ≤ 128K
    $1.75/1M $14.00/1M 输出 cache $0.17/1M
    推理能力稳健
  18. #298
    OpenAI: GPT-5.2 (batch) OpenAI 文档视觉模型

    GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

    工具 视觉 文档 推理 结构化
    上下文 400K 输出 ≤ 128K
    $0.88/1M $7.00/1M 输出 cache $0.09/1M
    推理能力稳健
  19. #299
    Z.ai: GLM 4.6V Zhipu 智谱 视觉多模态

    GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...

    工具 视觉 视频 推理 结构化
    上下文 131K 输出 ≤ 32K
    $0.30/1M $0.90/1M 输出 cache $0.06/1M
    推理能力稳健
  20. #300
    OpenAI: GPT-5.1-Codex-Max OpenAI 视觉多模态

    GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...

    工具 视觉 推理 结构化
    上下文 400K 输出 ≤ 128K
    $1.25/1M $10.00/1M 输出 cache $0.12/1M
    推理能力稳健