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)
GPT-4o · 2 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 | HU Hunyuan-TurboS腾讯AI实验室 | CL Claude 3.5 Sonnet NewAnthropic | GP GPT-4oOpenAI | LL Llama3.1-405B InstructFacebook AI研究实验室 |
|---|---|---|---|---|
Model snapshots | ||||
Organization | 腾讯AI实验室 | Anthropic | OpenAI | Facebook AI研究实验室 |
模型全名 | Hunyuan-TurboS | Claude 3.5 Sonnet New | GPT-4 Omni | Llama3.1-405B Instruct |
模型简介 | Not provided | Not provided | Not provided | Not provided |
模型类型 | 推理大模型 | 聊天大模型 | 多模态大模型 | 基础大模型 |
模型代号 | Hunyuan-TurboS | claude-3_5-sonnet-new | gpt-4o | Llama3_1-405B-Instruct |
Release | 2025-03-10 | 2024-10-22 | 2024-05-13 | 2024-07-23 |
MoE | No | No | No | No |
规格与性能 | ||||
Context length | 128K | 200K | 128K | 128K |
Parameters | — | — | — | 4050 |
激活参数量 | Not provided | Not provided | Not provided | Not provided |
模型规模 | 100b | 未知 | 未知 | 100b |
模型大小 | Not provided | Not provided | Not provided | 800GB |
推理速度 | Not provided | Not provided | Not provided | |
推理等级 | Not provided | Not provided | Not provided | |
最大输出 | Not provided | Not provided | 16384 | Not provided |
Supported modes | No mode data | No mode data | 常规模式（Non-Thinking Mode） | No mode data |
开源与许可 | ||||
Code Open Source | Not provided | Not provided | Not provided | Not provided |
Weights Open Source | Not provided | Not provided | Not provided | Not provided |
Commercial use | 不开源 | 不开源 | 不开源 | 免费商用授权 |
Modality support | ||||
Text Input/Output | Not provided | Not provided | / | Not provided |
Image Input/Output | Not provided | Not provided | / | Not provided |
Audio Input/Output | Not provided | Not provided | / | Not provided |
Video Input/Output | Not provided | Not provided | / | Not provided |
Embedding Input/Output | Not provided | Not provided | / | Not provided |
API 接口详情 | ||||
Text 价格 | Not provided | Not provided | Input: 2.5 美元/100万 tokensOutput: 10 美元/100万 tokens | Not provided |
Image API pricing | Not provided | Not provided | Input: 2.5 美元/100万 tokens | 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 | Not provided | Not provided | Not provided | Repo |
Hugging Face | Not provided | Not provided | Not provided | Model Page |
Official Page | Not provided | Not provided | Not provided | Not provided |
Guides | Not provided | Not provided | Not provided | Not provided |
Papers | Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku | Hello GPT-4o | models/llama3_1/MODEL_CARD.md | |
DataLearnerAI | 腾讯发布了一个全新的大模型Hunyuan Turbo S：号称评测效果超过GTP-4o和DeepSeek V3等模型，但没有开源或者放开使用 | Anthropic发布新一代Claude 3.5模型：全新的Haiku 3.5和升级版Sonnet 3.5 | Not provided | 重磅！MetaAI开源4050亿参数的大语言模型Llama3.1-405B模型！多项评测结果超越GPT-4o，与Claude-3.5 Sonnet平分秋色！ |
API pricing
Side-by-side input/output token pricing