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:3 分钟前(2026-11-20 02:59)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 |
-
#381
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
工具 推理上下文 128K 输出 ≤ 16K$0.45/1M $3.50/1M 输出工具调用能力扎实 -
#382
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
工具 结构化上下文 262K 输出 ≤ 65K$0.30/1M $1.00/1M 输出 cache $0.10/1M工具调用能力扎实 -
#383
UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...
视觉 结构化上下文 128K 输出 ≤ 2K$0.10/1M $0.20/1M 输出 cache $0.10/1M工具调用能力扎实 -
#384
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
工具 视觉 音频 视频 文档 推理 结构化上下文 1.0M 输出 ≤ 65K$0.10/1M $0.40/1M 输出 cache $0.01/1M工具调用能力扎实 -
#385
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
工具 结构化上下文 262K 输出 ≤ 117K$0.14/1M $0.80/1M 输出 cache $0.05/1M工具调用能力扎实 -
#386
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
工具上下文 131K 输出 ≤ 98K$0.57/1M $2.30/1M 输出工具调用能力扎实 -
#387
Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...
结构化上下文 128K 输出 ≤ 8K$0.20/1M $0.90/1M 输出工具调用能力扎实 -
#388
Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...
结构化上下文 262K 输出 ≤ 131K$0.90/1M $1.90/1M 输出工具调用能力扎实 -
#389
Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...
结构化上下文 262K 输出 ≤ 131K$0.45/1M $0.95/1M 输出工具调用能力扎实 -
#390
Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...
结构化上下文 262K 输出 ≤ 131K$0.80/1M $1.20/1M 输出工具调用能力扎实 -
#391
Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...
上下文 81K 输出 ≤ 38K$0.40/1M $0.60/1M 输出工具调用能力扎实 -
#392
Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...
工具 视觉 结构化上下文 256K 输出 ≤ 16K$0.07/1M $0.20/1M 输出工具调用能力扎实 -
#393
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...
工具 视觉 音频 视频 文档 推理 结构化上下文 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 -
#394
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
工具 视觉 音频 视频 文档 推理 结构化上下文 1.0M 输出 ≤ 65K$1.25/1M $10.00/1M 输出 cache $0.12/1M工具调用能力扎实 -
#395
The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
工具 视觉 文档 推理 结构化上下文 200K 输出 ≤ 100K$20.00/1M $80.00/1M 输出工具调用能力扎实 -
#396
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
工具 视觉 音频 文档 推理 结构化上下文 1.0M 输出 ≤ 65K$1.25/1M $10.00/1M 输出 cache $0.12/1M工具调用能力扎实 -
#397
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
工具 推理 结构化上下文 163K 输出 ≤ 32K$0.57/1M $2.29/1M 输出工具调用能力扎实 -
#398
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...
工具 视觉 文档 结构化上下文 131K 输出 ≤ 104K$0.44/1M $2.20/1M 输出 cache $0.04/1M工具调用能力扎实 -
#399
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
视觉上下文 163K 输出 ≤ 16K$0.18/1M $0.18/1M 输出工具调用能力扎实 -
#400
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
工具 推理 结构化上下文 40K 输出 ≤ 16K$0.12/1M $0.50/1M 输出工具调用能力扎实