加载中...
加载中...
See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 4 个模型的评测数据与核心参数。
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Best Overall
—
Best Single
—
Thinking Mode (Default)
Qwen3-235B-A22B-2507 · 1 Modality support
Higher is usually better; “—” means no score.
Complete scores for each model/mode across selected benchmarks.
Feature compare
Licensing, MoE architecture, and multi-modality support.
| Features & specs | QW Qwen3-235B-A22B-2507阿里巴巴 | QW Qwen3-235B-A22B阿里巴巴 | DE DeepSeek-V3-0324DeepSeek-AI | KI Kimi K2Moonshot AI |
|---|---|---|---|---|
Model snapshots | ||||
Organization | 阿里巴巴 | 阿里巴巴 | DeepSeek-AI | Moonshot AI |
模型全名 | Qwen3-235B-A22B-Instruct-2507 | Qwen3-235B-A22B | DeepSeek-V3-0324 | Kimi-K2-0711-Preview |
模型简介 | Not provided | Not provided | Not provided | Not provided |
模型类型 | 聊天大模型 | 推理大模型 | 聊天大模型 | 聊天大模型 |
模型代号 | Qwen3-235B-A22B-Instruct-2507 | Qwen3-235B-A22B | DeepSeek-V3-0324 | kimi-k2-0711-base-preview |
Release | 2025-07-21 | 2025-04-28 | 2025-03-24 | 2025-07-11 |
MoE | Yes | Yes | Yes | Yes |
规格与性能 | ||||
Context length | 256K | 128K | 128K | 131K |
Parameters | 2350 | 2350 | 6710 | 10000 |
激活参数量 | 220 | 220 | 370 | 320 |
模型规模 | 100b | 100b | 100b | 100b |
模型大小 | 470.77 GB | 470GB | 1442GB | 1.01TB |
推理速度 | ||||
推理等级 | ||||
最大输出 | 32768 | 16384 | Not provided | 134144 |
Supported modes | 常规模式（Non-Thinking Mode） | 常规模式（Non-Thinking Mode）思考模式（Thinking Mode） | 常规模式（Non-Thinking Mode） | 常规模式（Non-Thinking Mode） |
开源与许可 | ||||
Code Open Source | Not provided | Not provided | Closed Source | Not provided |
Weights Open Source | Not provided | Not provided | Closed Source | Not provided |
Commercial use | 免费商用授权 | 免费商用授权 | 免费商用授权 | 免费商用授权 |
Modality support | ||||
Text Input/Output | / | / | / | / |
Image Input/Output | / | / | / | / |
Audio Input/Output | / | / | / | / |
Video Input/Output | / | / | / | / |
Embedding Input/Output | / | / | / | / |
API 接口详情 | ||||
Text 价格 | Input: 0.7 美元/100 万tokensOutput: 2.8 美元/100 万tokens | Input: 0.7 美元/100 万tokensOutput: 8.4 美元/100 万tokens | Input: 0.27 美元/100万 tokensOutput: 1.1 美元/100万 tokens | Input: 0.6 美元/100 万tokensOutput: 2.5 美元/100 万tokens |
Image API pricing | Not provided | Not provided | Not provided | Not provided |
Audio API pricing | Not provided | Not provided | Not provided | Not provided |
Video API pricing | Not provided | Not provided | Not provided | Not provided |
Embedding API pricing | Not provided | Not provided | Not provided | Not provided |
Resources | ||||
GitHub | Repo | Repo | Repo | Repo |
Hugging Face | Model Page | Model Page | Model Page | Model Page |
Official Page | Not provided | Not provided | Not provided | Not provided |
Guides | Not provided | Not provided | Not provided | Not provided |
Papers | Qwen3: Think Deeper, Act Faster | Qwen3: Think Deeper, Act Faster | Kimi K2: Open Agentic Intelligence | |
DataLearnerAI | 阿里发布Qwen3小幅更新版本，放弃混合思考模式，发布全新的2个版本Qwen3-235B-A22B-2507模型，1/5的参数，性能直逼Kimi K2，推理模式版本评测结果接近o3 | 重磅！阿里开源第三代千问大模型：Qwen3系列，最小仅6亿参数规模，最大2350亿参数规模大模型！ | DeepSeekV3-0324发布：DeepSeek V3基础上大幅升级推理能力和前端网页的美观度，多项评测结果超过GPT-4.5 | Kimi开源K2大模型：全球首个开源可商用的1万亿参数规模大模型，MoE架构，评测结果与DeepSeekV3相当，但模型文件有1TB！ |
API pricing
Side-by-side input/output token pricing