한국어(KO) 1,800억 파라미터가 2조8천억을 이겼다: SuperCLUE 11월 수학·과학 추론 오픈소스 1위 Darwin의 효율과 다운로드

Darwin-180B-RSI：1800亿参数模型领跑开源LLM排行榜

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-13 01:03

Vidraft Lab推出的开源大语言模型Darwin-180B-RSI在SuperCLUE十一月数学和科学推理评估中，位列开源模型第一名，综合排名第二。该模型拥有1800亿参数，在数学和科学推理方面得分比2.8万亿参数的Kimi-K3.1-Pro高出10多分，而模型规模仅为其约1/16。该模型的效率和更小的体积预示着其在成本效益企业级AI解决方案和设备端应用方面的潜力，有望减少对外国硬件和云基础设施的依赖。 AI

影响为高效LLM树立了新标杆，有望降低企业AI成本并支持设备端应用。

排序理由发布了新的开源模型，其基准测试结果超越了更大的模型。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 57 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Significant; 发布了新的开源模型，其基准测试结果超越了更大的模型。[lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

dev.to — LLM tag TIER_1 한국어(KO) · Vidraft_lab · 2026-11-13 01:03

1800亿参数模型超越2.8万亿参数模型：SuperCLUE十一月数理推理开源榜第一 Darwin效率与下载量

<h2> TL;DR </h2> <p>비드래프트의 오픈소스 거대언어모델(LLM) <a href="https://huggingface.co/FINAL-Bench/Darwin-180B-RSI-R3" rel="noopener noreferrer">Darwin-180B-RSI</a>가 SuperCLUE 2026년 11월 평가 수학·과학 추론에서 73.68점을 받아 오픈소스(공개 가중치) 모델 세계 1위, 전체 2위에 올랐습니다. 1,800억 파라미터 모델이 같은 평가에 오른 2조8천억 파라미터 모델 Kim…

本文如何被排名

报道来源 [1]

1800亿参数模型超越2.8万亿参数模型：SuperCLUE十一月数理推理开源榜第一 Darwin效率与下载量

相关实体

相关话题