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:6 分钟前(2026-11-20 01:59)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。
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
⚡ 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 |
-
#321
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工具调用能力扎实 -
#322
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
工具 文档 结构化上下文 262K 输出 ≤ 209K$0.40/1M $2.00/1M 输出 cache $0.04/1M工具调用能力扎实 -
#323
The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...
工具 结构化上下文 256K 输出 ≤ 128K$1.00/1M $3.00/1M 输出工具调用能力扎实 -
#324
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 $0.05/1M工具调用能力扎实 -
#325
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工具调用能力扎实 -
#326
Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...
工具 视觉 视频 文档 推理上下文 1M 输出 ≤ 65K$0.30/1M $2.50/1M 输出工具调用能力扎实 -
#327
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...
工具 视觉 结构化上下文 262K 输出 ≤ 209K$0.20/1M $0.20/1M 输出 cache $0.02/1M工具调用能力扎实 -
#328
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
工具 视觉 结构化上下文 262K 输出 ≤ 209K$0.15/1M $0.15/1M 输出 cache $0.01/1M工具调用能力扎实 -
#329
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
工具 视觉 结构化上下文 131K 输出 ≤ 104K$0.10/1M $0.10/1M 输出 cache $0.01/1M工具调用能力扎实 -
#330
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
工具 视觉 文档 结构化上下文 262K 输出 ≤ 209K$0.50/1M $1.50/1M 输出 cache $0.05/1M工具调用能力扎实 -
#331
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
工具 推理 结构化上下文 163K 输出 ≤ 147K$0.26/1M $0.38/1M 输出 cache $0.13/1M工具调用能力扎实 -
#332
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
工具 视觉 文档 推理 结构化上下文 200K 输出 ≤ 64K$5.00/1M $25.00/1M 输出 cache $0.50/1M工具调用能力扎实 -
#333
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
工具 视觉 文档 推理 结构化上下文 200K 输出 ≤ 64K$2.50/1M $12.50/1M 输出 cache $0.25/1M工具调用能力扎实 -
#334
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
视觉 推理 结构化 生图上下文 65K 输出 ≤ 32K$2.00/1M $12.00/1M 输出 cache $0.20/1M工具调用能力扎实 -
#335
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...
工具 视觉 文档 推理 结构化上下文 400K 输出 ≤ 128K$1.25/1M $10.00/1M 输出 cache $0.12/1M工具调用能力扎实 -
#336
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...
工具 视觉 文档 推理 结构化上下文 400K 输出 ≤ 128K$0.62/1M $5.00/1M 输出 cache $0.06/1M工具调用能力扎实 -
#337
GPT-5.1-Codex is a specialized version of GPT-5.1 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$1.25/1M $10.00/1M 输出 cache $0.13/1M工具调用能力扎实 -
#338
GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
工具 视觉 推理 结构化上下文 400K 输出 ≤ 128K$0.25/1M $2.00/1M 输出 cache $0.03/1M工具调用能力扎实 -
#339
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
工具 推理 结构化上下文 262K 输出 ≤ 98K$0.60/1M $2.50/1M 输出 cache $0.15/1M工具调用能力扎实 -
#340
Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.
工具 视觉上下文 1M 输出 ≤ 32K$2.50/1M $12.50/1M 输出 cache $0.62/1M工具调用能力扎实