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:58 分钟前(2026-11-18 10:41)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 5.1 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 |
-
#121
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
工具 视觉 视频 推理 结构化智能 0.0智能体 1.2上下文 262K 输出 ≤ 40K$0.17/1M $0.25/1M 输出 cache $0.15/1M工具调用能力扎实 -
#122
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
工具 推理 结构化智能 0.0智能体 1.2上下文 131K 输出 ≤ 117K$0.02/1M $0.09/1M 输出 cache $0.01/1M工具调用能力扎实 -
#123
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
工具 推理 结构化智能 0.0智能体 1.2上下文 131K 输出 ≤ 117K$0.02/1M $0.11/1M 输出工具调用能力扎实 -
#124
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
工具 推理智能 3.4智能体 1.1上下文 256K 输出 ≤ 64K免费免费可调 · 限时白嫖 -
#125
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 结构化智能 0.0智能体 1.1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 -
#126
Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...
工具 视觉 推理 结构化智能 6.2智能体 1.0上下文 192K 输出 ≤ 64K$0.30/1M $1.50/1M 输出 cache $0.15/1M工具调用能力扎实 -
#127
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 结构化智能 0.0智能体 1.0上下文 262K 输出 ≤ 235K$0.06/1M $0.24/1M 输出 cache $0.01/1M工具调用能力扎实 -
#128
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 结构化智能 0.0智能体 1.0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 -
#129
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
工具 结构化智能 0.0智能体 0.9上下文 262K 输出 ≤ 235K$0.12/1M $0.80/1M 输出 cache $0.07/1M工具调用能力扎实 -
#130
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
工具 推理 结构化智能 0.0智能体 0.9上下文 40K 输出 ≤ 16K$0.12/1M $0.24/1M 输出工具调用能力扎实 -
#131
Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
工具 推理 结构化智能 0.0智能体 0.9上下文 131K 输出 ≤ 16K$0.08/1M $0.28/1M 输出工具调用能力扎实 -
#132
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
工具 视觉 推理 结构化智能 4.3智能体 0.8上下文 262K 输出 ≤ 209K$0.15/1M $0.60/1M 输出 cache $0.01/1M工具调用能力扎实 -
#133
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 结构化智能 0.0智能体 0.8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 -
#134
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
工具 结构化智能 0.0智能体 0.8上下文 163K 输出 ≤ 115K$0.29/1M $1.14/1M 输出 cache $0.11/1M工具调用能力扎实 -
#135
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 结构化智能 0.0智能体 0.6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 -
#136
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
工具 视觉 结构化智能 0.0智能体 0.6上下文 524K 输出 ≤ 32K$0.35/1M $1.00/1M 输出 cache $0.17/1M工具调用能力扎实 -
#137
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
工具 视觉 结构化智能 0.0智能体 0.5上下文 1.3M 输出 ≤ 16K$0.10/1M $0.30/1M 输出工具调用能力扎实 -
#138
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
工具 视觉 结构化智能 0.0智能体 0.1上下文 131K 输出 ≤ 16K$0.05/1M $0.15/1M 输出工具调用能力扎实 -
#139
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
工具 视觉 结构化智能 0.0智能体 0.1上下文 131K 输出 ≤ 117K$0.08/1M $0.45/1M 输出 cache $0.04/1M工具调用能力扎实 -
#140
Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...
工具 视觉 文档 推理 结构化智能 64.6智能体 0.0上下文 1M 输出 ≤ 128K$8.00/1M $40.00/1M 输出 cache $0.20/1M工具调用能力扎实