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)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。
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 |
-
#421
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 -
#422
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 -
#423
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 -
#424
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 -
#425
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 -
#426
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 -
#427
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 -
#428
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 -
#429
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 -
#430
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 -
#431
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 -
#432
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 -
#433
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 -
#434
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 -
#435
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 -
#436
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 -
#437
[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 -
#438
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 -
#439
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 -
#440
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