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:10 分钟前(2026-11-18 12:41)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 |
-
#241
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...
结构化上下文 128K 输出 ≤ 8K$0.03/1M $0.15/1M 输出 cache $0.03/1M工具调用能力扎实 -
#242
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...
结构化上下文 128K 输出 ≤ 8K$0.05/1M $0.23/1M 输出 cache $0.05/1M工具调用能力扎实 -
#243
This model always redirects to the latest model in the GPT Astra family.
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$8.00/1M $40.00/1M 输出 cache $0.40/1M工具调用能力扎实 -
#244
This model always redirects to the latest model in the GPT Sol family.
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$2.00/1M $10.00/1M 输出 cache $0.10/1M工具调用能力扎实 -
#245
This model always redirects to the latest model in the GPT Terra family.
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$1.00/1M $5.00/1M 输出 cache $0.05/1M工具调用能力扎实 -
#246
This model always redirects to the latest model in the GPT Luna family.
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$0.10/1M $0.50/1M 输出 cache $0.01/1M工具调用能力扎实 -
#247
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...
工具 视觉 文档 推理 结构化 联网上下文 1M 输出 ≤ 128K$5.00/1M $30.00/1M 输出 cache $0.50/1M工具调用能力扎实 -
#248
Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
工具 视觉 文档 推理 结构化 联网上下文 1M 输出 ≤ 128K$2.00/1M $6.00/1M 输出 cache $0.25/1M工具调用能力扎实 -
#249
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
工具 视觉 推理 结构化上下文 1.0M 输出 ≤ 943K$0.05/1M $0.57/1M 输出 cache $0.02/1M工具调用能力扎实 -
#250
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
工具 视觉 推理 结构化上下文 1.0M 输出 ≤ 131K$0.11/1M $0.34/1M 输出 cache $0.00/1M工具调用能力扎实 -
#251
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
视觉 推理 结构化上下文 262K 输出 ≤ 235K$0.02/1M $0.10/1M 输出 cache $0.00/1M工具调用能力扎实 -
#252
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
工具 视觉 推理 结构化上下文 262K 输出 ≤ 235K$0.07/1M $0.25/1M 输出 cache $0.01/1M工具调用能力扎实 -
#253
GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$10.00/1M $50.00/1M 输出 cache $1.00/1M工具调用能力扎实 -
#254
GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
工具 视觉 文档 推理 结构化上下文 1.1M 输出 ≤ 128K$5.00/1M $25.00/1M 输出 cache $0.50/1M工具调用能力扎实 -
#255
Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...
工具 视觉 视频 文档 推理 结构化上下文 1.0M 输出 ≤ 943K$0.10/1M $0.20/1M 输出 cache $0.00/1M工具调用能力扎实 -
#256
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
工具 推理 结构化上下文 1.0M 输出 ≤ 64K$0.83/1M $2.50/1M 输出 cache $0.04/1M工具调用能力扎实 -
#257
This model always redirects to the latest model in the GLM Flash family.
工具 视觉 视频 推理 结构化上下文 1.0M 输出 ≤ 131K$0.04/1M $0.08/1M 输出 cache $0.03/1M工具调用能力扎实 -
#258
Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...
工具 视觉 视频 文档 推理 结构化上下文 1.0M 输出 ≤ 943K$0.10/1M $0.20/1M 输出 cache $0.00/1M工具调用能力扎实 -
#259
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...
上下文 8K 输出 ≤ 4K$0.04/1M $0.18/1M 输出工具调用能力扎实 -
#260
Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...
结构化上下文 8K 输出 ≤ 4K$0.07/1M $0.29/1M 输出工具调用能力扎实