LongCat 2.0开源
LongCat · 发布于 2026年6月29日
LongCat LongCat 2.0 model with 1.0M context window, optimized for advanced reasoning and multimodal tasks.
65.0
Podium 综合得分
第 215 名 / 共 693 个
Intelligence Rank
65.0#215
AAQI: 30.0
Output Speed
42 t/s
TTFT: ~2.85s · ITL: 23.8 ms/tok
Blended Price (3:1)
$1.3 /1M
In: $0.75/M · Out: $2.95/M · Cache: $0.075
Context Capacity
1.0M
≈ 2,500 A4 Pages (Max Out: 16384)
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
LongCat 2.0
Claude Mythos Preview (#1)
Average (68)
各榜单得分
分类能力得分
📜 Long Context90.0
💰 Value63.0
🧠 Reasoning45.0
📐 Math39.0
📚 Knowledge39.0
🤖 Agentic36.0
intelligence30.0
⚡ Speed14.0
基准测试分项
GPQA Diamond36%
模型详细参数
| 发布日期 | 2026年6月29日 |
|---|---|
| 参数量 | 1.6T (48B active) |
| 开源协议 | Open Weights |
| 上下文窗口 | 1,000,000 tokens |
| 输入价格 | $0.75/M |
| 输出价格 | $2.95/M |
| 输出速度 | 42 t/s |
| 首Token延迟 | 3 ms |
💰 Estimated Monthly Bill & TCO Calculator
Estimated Monthly Spend
$0.00
Calculating savings vs GPT-4o...
🔖 Embed Badges & Citation Snippet
GitHub Markdown Badge
[](https://llmpodium.com/models/longcat-2-0)BibTeX Citation
@misc{llmpodium2026longcat20,
title = {Benchmark Analysis and Intelligence Evaluation of LongCat 2.0},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/longcat-2-0}
}正面比较
最佳模型
model.alternatives_title
model.alternatives_desc