跳到主内容
智客 ZICQ

智能体与工具调用榜

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

依据 OpenRouter benchmarks.agentic_index(智能体 / 工具调用指数),结合 supported_parameters.tools 标记,给做 Agent 框架的极客参考。

📊 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 · 智能体指数 Anthropic: Claude Fable 5.1 57.2
⚡ 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 5.1 Anthropic Anthropic: Claude Fable 5.1 (batch) Anthropic Anthropic: Claude Opus 5 Anthropic
综合智能 / 编码 / 智能体 50.0 / 80.7 / 57.2 50.0 / 80.7 / 57.2 44.2 / 78.0 / 56.5
上下文窗口 1M tokens 1M tokens 1M tokens
输入 / 输出单价 (1M) $10.00 / $50.00 $5.00 / $25.00 $5.00 / $25.00
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. #81
    OpenAI: GPT-5.4 Nano (batch) OpenAI 文档视觉模型 有基准

    GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

    工具 视觉 文档 推理 结构化
    智能 0.0
    智能体 16.0
    上下文 400K 输出 ≤ 128K
    $0.10/1M $0.62/1M 输出 cache $0.01/1M
    工具调用能力扎实
  2. #82
    Xiaomi: MiMo-V2.5 Xiaomi 音视频多模态 有基准

    MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

    工具 视觉 音频 视频 推理 结构化
    智能 0.0
    智能体 15.8
    上下文 1M 输出 ≤ 65K
    $0.40/1M $2.00/1M 输出 cache $0.08/1M
    工具调用能力扎实
  3. #83
    Anthropic: Claude Sonnet 4.5 Anthropic 文档视觉模型 有基准

    Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

    工具 视觉 文档 推理 结构化
    智能 0.0
    智能体 15.8
    上下文 1M 输出 ≤ 64K
    $3.00/1M $15.00/1M 输出 cache $0.30/1M
    工具调用能力扎实
  4. #84
    Anthropic: Claude Sonnet 4.5 (batch) Anthropic 文档视觉模型 有基准

    Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

    工具 视觉 文档 推理 结构化
    智能 0.0
    智能体 15.8
    上下文 1M 输出 ≤ 64K
    $1.50/1M $7.50/1M 输出 cache $0.15/1M
    工具调用能力扎实
  5. #85
    xAI: Grok 4.3 xAI 文档视觉模型 有基准

    Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

    工具 视觉 文档 推理 结构化
    智能 0.0
    智能体 15.5
    上下文 1M 输出 ≤ 900K
    $1.25/1M $2.50/1M 输出 cache $0.20/1M
    工具调用能力扎实
  6. #86
    xAI: Grok 4.3 (batch) xAI 文档视觉模型 有基准

    Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

    工具 视觉 文档 推理 结构化
    智能 0.0
    智能体 15.5
    上下文 1M 输出 ≤ 900K
    $1.00/1M $2.00/1M 输出 cache $0.16/1M
    工具调用能力扎实
  7. #87
    MiniMax: MiniMax M2.7 MiniMax 通用大语言模型 有基准

    MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

    工具 推理 结构化
    智能 0.0
    智能体 15.3
    上下文 196K 输出 ≤ 176K
    $0.21/1M $0.84/1M 输出 cache $0.04/1M
    工具调用能力扎实
  8. #88
    Google: Gemini 3.5 Flash Lite Google DeepMind 音视频多模态 有基准

    Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

    工具 视觉 音频 视频 文档 推理 结构化
    智能 11.7
    智能体 14.3
    上下文 1.0M 输出 ≤ 65K
    $0.30/1M $2.50/1M 输出 cache $0.03/1M
    工具调用能力扎实
  9. #89
    Google: Gemini 3.5 Flash Lite (batch) Google DeepMind 音视频多模态 有基准

    Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

    工具 视觉 音频 视频 文档 推理 结构化
    智能 11.7
    智能体 14.3
    上下文 1.0M 输出 ≤ 65K
    $0.15/1M $1.25/1M 输出 cache $0.01/1M
    工具调用能力扎实
  10. #90
    Meituan: LongCat 2.0 Meituan 通用大语言模型 有基准

    LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...

    工具 推理
    智能 0.0
    智能体 14.0
    上下文 1.0M 输出 ≤ 262K
    $0.30/1M $1.20/1M 输出 cache $0.01/1M
    工具调用能力扎实
  11. #91
    Qwen: Qwen3.6 35B A3B Alibaba 通义 视觉多模态 有基准

    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

    工具 视觉 视频 推理 结构化
    智能 0.0
    智能体 13.1
    上下文 262K 输出 ≤ 235K
    $0.10/1M $0.90/1M 输出 cache $0.02/1M
    工具调用能力扎实
  12. #92
    Meta: Muse Glimmer 30B Meta 视觉多模态 有基准

    Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

    工具 视觉 推理 结构化
    智能 6.3
    智能体 8.5
    上下文 131K 输出 ≤ 117K
    $0.35/1M $1.50/1M 输出 cache $0.04/1M
    工具调用能力扎实
  13. #93
    Meta: Muse Glimmer 30B (batch) Meta 视觉多模态 有基准

    Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

    工具 视觉 推理 结构化
    智能 6.3
    智能体 8.5
    上下文 131K 输出 ≤ 16K
    $0.24/1M $0.96/1M 输出 cache $0.03/1M
    工具调用能力扎实
  14. #94
    Qwen: Qwen3.5 397B A17B Alibaba 通义 视觉多模态 有基准

    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
    智能 0.0
    智能体 8.3
    上下文 262K 输出 ≤ 81K
    $0.45/1M $3.00/1M 输出 cache $0.22/1M
    工具调用能力扎实
  15. #95
    Google: Gemini 3.1 Pro Preview Google DeepMind 音视频多模态 有基准

    Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

    工具 视觉 音频 视频 文档 推理 结构化
    智能 0.0
    智能体 8.2
    上下文 1.0M 输出 ≤ 65K
    $2.00/1M $12.00/1M 输出 cache $0.20/1M
    工具调用能力扎实
  16. #96
    Google: Gemini 3.1 Pro Preview (batch) Google DeepMind 音视频多模态 有基准

    Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

    工具 视觉 音频 视频 文档 推理 结构化
    智能 0.0
    智能体 8.2
    上下文 1.0M 输出 ≤ 65K
    $1.00/1M $6.00/1M 输出
    工具调用能力扎实
  17. #97
    Anthropic: Claude Haiku 4.5 Anthropic 文档视觉模型 有基准

    Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

    工具 视觉 文档 推理 结构化
    智能 7.4
    智能体 8.0
    上下文 200K 输出 ≤ 64K
    $1.00/1M $5.00/1M 输出 cache $0.10/1M
    工具调用能力扎实
  18. #98
    Anthropic: Claude Haiku 4.5 (batch) Anthropic 文档视觉模型 有基准

    Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

    工具 视觉 文档 推理 结构化
    智能 7.4
    智能体 8.0
    上下文 200K 输出 ≤ 64K
    $0.50/1M $2.50/1M 输出 cache $0.05/1M
    工具调用能力扎实
  19. #99
    Qwen: Qwen3.5-122B-A10B Alibaba 通义 视觉多模态 有基准

    The Qwen3.5 122B-A10B 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. In terms of...

    工具 视觉 视频 推理 结构化
    智能 0.0
    智能体 7.6
    上下文 262K 输出 ≤ 65K
    $0.26/1M $2.08/1M 输出
    工具调用能力扎实
  20. #100
    Mistral: Mistral Medium 3.5 Mistral AI 文档视觉模型 有基准

    Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

    工具 视觉 文档 推理 结构化
    智能 4.6
    智能体 7.0
    上下文 262K 输出 ≤ 209K
    $1.50/1M $7.50/1M 输出
    工具调用能力扎实