工具调用 (Function Call) 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:51 分钟前(2026-11-19 03:12)数据来源与评测方法
声明支持 tools / tool_choice 的模型,按 Agentic 指数 + 工具加成排序。
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 | OpenAI: GPT-6.2 Astra Pro OpenAI | OpenAI: GPT-6.2 Astra Pro (batch) OpenAI | OpenAI: GPT-6.2 Astra OpenAI |
|---|---|---|---|
| 综合智能 / 编码 / 智能体 | — | — | 62.1 / 0.0 / 0.0 |
| 上下文窗口 | 1.1M tokens | 1.1M 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 |
-
#41
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
工具 视觉 推理 结构化上下文 1.0M 输出 ≤ 943K$0.04/1M $0.15/1M 输出 cache $0.00/1MFunction Call 稳定 -
#42
Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
工具 视觉 视频 推理 结构化上下文 262K 输出 ≤ 256K$0.60/1M $3.00/1M 输出 cache $0.06/1MFunction Call 稳定 -
#43
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 结构化上下文 1.0M 输出 ≤ 943K$0.30/1M $1.00/1M 输出 cache $0.04/1MFunction Call 稳定 -
#44
Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...
工具 视觉 推理 结构化上下文 262K 输出 ≤ 65K$0.08/1M $0.13/1M 输出 cache $0.04/1MFunction Call 稳定 -
#45
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 结构化上下文 1.0M 输出 ≤ 943K$1.25/1M $4.25/1M 输出 cache $0.15/1MFunction Call 稳定 -
#46
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 结构化上下文 1.0M 输出 ≤ 235K$0.15/1M $0.50/1M 输出 cache $0.02/1MFunction Call 稳定 -
#47
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 结构化上下文 1M 输出 ≤ 131K免费免费可调 · 限时白嫖 -
#48
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
工具 视觉上下文 1.0M 输出 ≤ 131K$0.80/1M $3.20/1M 输出 cache $0.03/1MFunction Call 稳定 -
#49
This model always redirects to the latest model in the Pareto family.
工具 视觉上下文 1.0M 输出 ≤ 131K$0.80/1M $3.20/1M 输出 cache $0.03/1MFunction Call 稳定 -
#50
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
工具 视觉 结构化上下文 262K 输出 ≤ 131K$2.50/1M $7.50/1M 输出 cache $0.25/1MFunction Call 稳定 -
#51
LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...
工具 推理 结构化上下文 128K 输出 ≤ 8K$0.05/1M $0.70/1M 输出 cache $0.02/1MFunction Call 稳定 -
#52
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
工具 视觉 音频 视频 文档 推理 结构化上下文 1.0M 输出 ≤ 943K$2.00/1M $10.00/1M 输出 cache $0.10/1MFunction Call 稳定 -
#53
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
工具 视觉 音频 视频 文档 推理 结构化上下文 1.0M 输出 ≤ 943K$1.00/1M $5.00/1M 输出 cache $0.05/1MFunction Call 稳定 -
#54
Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
工具 视觉 音频 视频 文档 推理 结构化上下文 1.0M 输出 ≤ 943K$4.00/1M $20.00/1M 输出 cache $0.20/1MFunction Call 稳定 -
#55
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...
工具 视觉 视频 推理 结构化上下文 1M 输出 ≤ 64K$1.00/1M $2.70/1M 输出 cache $0.10/1MFunction Call 稳定 -
#56
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
工具 视觉 文档 推理 结构化上下文 1M 输出 ≤ 128K$0.10/1M $0.50/1M 输出 cache $0.01/1MFunction Call 稳定 -
#57
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
工具 视觉 文档 推理 结构化上下文 1M 输出 ≤ 128K$0.05/1M $0.25/1M 输出 cache $0.01/1MFunction Call 稳定 -
#58
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...
工具 视觉 推理 结构化 生图上下文 65K 输出 ≤ 58K$1.50/1M $7.50/1M 输出Function Call 稳定 -
#59
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 结构化上下文 1.0M 输出 ≤ 262K$0.70/1M $2.10/1M 输出 cache $0.07/1MFunction Call 稳定 -
#60
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
工具 推理上下文 1M 输出 ≤ 262K$0.04/1M $0.14/1M 输出 cache $0.01/1MFunction Call 稳定