跳到主内容
智客 ZICQ

逻辑推理榜

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:48 分钟前(2026-11-21 03:34)
清除
数据来源与评测方法

声明支持 reasoning 推理 effort 的模型,按 Intelligence 指数排序。

📊 评测基准与方法论说明
1. 数据来源:模型元数据与调用价格每小时自 OpenRouter (openrouter.ai) 官方接口同步,包含商业模型、开源权重及实验预览版本。
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
当前榜单模型数 477
免费可调 15
支持视觉 335
支持工具调用 415
支持推理 360
最长上下文 SpaceXSI: Grok 4.20 Multi-Agent 2M tokens
已知输入价格均值 $1.57 / 1M 美元 / 百万 token
最低价模型 inclusionAI: Ling 3.0 Tiny $0.015 / 1M
当前维度 TOP · 智能指数 Anthropic: Claude Fable 5.2 64.6
⚡ 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
  1. #421
    Meta: Llama 4 Maverick Meta 视觉多模态

    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
    上下文 524K 输出 ≤ 32K
    $0.35/1M $1.00/1M 输出 cache $0.17/1M
    推理能力稳健
  2. #422
    Meta: Llama 4 Scout Meta 视觉多模态

    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
    上下文 1.3M 输出 ≤ 16K
    $0.10/1M $0.30/1M 输出
    推理能力稳健
  3. #423
    DeepSeek: DeepSeek V3 0324 DeepSeek 通用大语言模型

    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
    上下文 163K 输出 ≤ 115K
    $0.29/1M $1.14/1M 输出 cache $0.11/1M
    推理能力稳健
  4. #424
    Mistral: Mistral Small 3.1 24B Mistral AI 视觉多模态

    Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

    工具 视觉 结构化
    上下文 128K 输出 ≤ 102K
    $0.35/1M $0.55/1M 输出
    推理能力稳健
  5. #425
    Google: Gemma 3 4B Google DeepMind 视觉多模态

    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,...

    视觉 结构化
    上下文 131K 输出 ≤ 16K
    $0.05/1M $0.10/1M 输出
    推理能力稳健
  6. #426
    Google: Gemma 3 12B Google DeepMind 视觉多模态

    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
    上下文 131K 输出 ≤ 16K
    $0.05/1M $0.15/1M 输出
    推理能力稳健
  7. #427
    Cohere: Command A Cohere 通用大语言模型

    Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

    工具 结构化
    上下文 256K 输出 ≤ 8K
    $2.50/1M $10.00/1M 输出
    推理能力稳健
  8. #428
    Google: Gemma 3 27B Google DeepMind 视觉多模态

    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
    上下文 131K 输出 ≤ 117K
    $0.08/1M $0.45/1M 输出 cache $0.04/1M
    推理能力稳健
  9. #429
    TheDrummer: Skyfall 36B V2 Thedrummer 通用大语言模型

    Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

    结构化
    上下文 32K 输出 ≤ 29K
    $0.55/1M $0.80/1M 输出 cache $0.25/1M
    推理能力稳健
  10. #430
    Perplexity: Sonar Pro Perplexity 视觉多模态

    Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...

    视觉 联网
    上下文 200K 输出 ≤ 8K
    $3.00/1M $15.00/1M 输出
    推理能力稳健
  11. #431
    Mistral: Saba Mistral AI 通用大语言模型

    Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...

    工具 文档 结构化
    上下文 32K 输出 ≤ 26K
    $0.20/1M $0.60/1M 输出 cache $0.02/1M
    推理能力稳健
  12. #432
    AionLabs: Aion-RP 1.0 (8B) Aion-Labs 通用大语言模型

    Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

    上下文 32K 输出 ≤ 29K
    $0.80/1M $1.60/1M 输出
    推理能力稳健
  13. #433
    Qwen: Qwen2.5 VL 72B Instruct Alibaba 通义 视觉多模态

    Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

    视觉 结构化
    上下文 128K 输出 ≤ 115K
    $0.80/1M $1.00/1M 输出 cache $0.40/1M
    推理能力稳健
  14. #434
    Qwen: Qwen-Plus Alibaba 通义 通用大语言模型

    Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

    工具 结构化
    上下文 1M 输出 ≤ 32K
    $0.26/1M $0.78/1M 输出 cache $0.05/1M
    推理能力稳健
  15. #435
    Mistral: Mistral Small 3 Mistral AI 通用大语言模型

    Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

    结构化
    上下文 32K 输出 ≤ 16K
    $0.05/1M $0.08/1M 输出
    推理能力稳健
  16. #436
    Perplexity: Sonar Perplexity 视觉多模态

    Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...

    视觉 联网
    上下文 127K 输出 ≤ 114K
    $1.00/1M $1.00/1M 输出
    推理能力稳健
  17. #437
    Microsoft: Phi 4 Microsoft 通用大语言模型

    [Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

    结构化
    上下文 16K 输出 ≤ 14K
    $0.07/1M $0.14/1M 输出
    推理能力稳健
  18. #438
    DeepSeek: DeepSeek V3 DeepSeek 通用大语言模型

    DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

    工具 结构化
    上下文 163K 输出 ≤ 16K
    $0.26/1M $1.03/1M 输出
    推理能力稳健
  19. #439
    Cohere: Command R7B (12-2024) Cohere 通用大语言模型

    Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

    工具 结构化
    上下文 128K 输出 ≤ 4K
    $0.04/1M $0.15/1M 输出
    推理能力稳健
  20. #440
    Meta: Llama 3.3 70B Instruct Meta 通用大语言模型

    The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

    工具 结构化
    上下文 131K 输出 ≤ 115K
    $0.71/1M $0.71/1M 输出 cache $0.71/1M
    推理能力稳健