PulseAugur
中
实时 17:17:48
English(EN) Darwin-180B-RSI Ranks #1 Open-Weight Model in Math and Science Reasoning on SuperCLUE (Nov 2026)

VIDRAFT 的 Darwin-180B-RSI-R3 在全球数学/科学推理方面排名第二

VIDRAFT 发布了 Darwin-180B-RSI-R3,这是一款开放权重的专家混合(Mixture-of-Experts)大型语言模型,它利用递归自我改进(Recursive Self-Improvement, RSI)来增强其推理能力,而无需新的人工标注数据。该模型在 SuperCLUE 2026年11月的评估中,在全球数学和科学推理方面取得了第二高的分数,表现优于多家主要人工智能实验室的知名模型。Darwin-180B-RSI-R3 基于 Alibaba 的 Qwen3.8-Flash-Next,通过问题生成、自我解答和验证的迭代过程更新其推理权重,同时其存储知识的专家层保持冻结状态。 AI

影响 展示了自我改进技术在增强开放权重模型推理能力方面的潜力。

排序理由 模型发布,来自非前沿实验室的基准测试结果。

在 dev.to — LLM tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →

VIDRAFT 的 Darwin-180B-RSI-R3 在全球数学/科学推理方面排名第二

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
模型发布,来自非前沿实验室的基准测试结果。
Source corroboration
5 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
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
3 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [5]

  1. dev.to — LLM tag TIER_1 한국어(KO) · Vidraft_lab ·

    Chosun Biz、Economist、Digital Daily 和 AI Times 报道 Darwin 的 SuperCLUE 结果:全球数学和科学推理第二名,开放权重第一名

    <h2> TL;DR </h2> <p>2026년 11월 6일 조선비즈, 이코노미스트, 디지털데일리, AI타임스 네 곳이 비드래프트의 오픈 가중치 추론 모델 <a href="https://huggingface.co/FINAL-Bench/Darwin-180B-RSI-R3" rel="noopener noreferrer">Darwin-180B-RSI-R3</a>가 SuperCLUE 2026년 11월 종합 평가에서 수학·과학 추론 73.68점을 받았다고 보도했습니다. 19개 모델 중 OpenAI GPT-6.…

  2. dev.to — LLM tag TIER_1 English(EN) · AI OpenFree ·

    Darwin-180B-RSI-R3:VIDRAFT 的自改进 MoE 模型在数学与科学推理方面全球排名第二

    <h1> Darwin-180B-RSI-R3: VIDRAFT's Self-Improving MoE Model Hits #2 in Math &amp; Science Reasoning Globally </h1> <blockquote> <p><strong>TL;DR:</strong> VIDRAFT's Darwin-180B-RSI-R3 is a 180B-parameter open-weight MoE model that applies Recursive Self-Improvement (RSI) to auton…

  3. dev.to — LLM tag TIER_1 Español(ES) · 김민식/학생 ·

    韩媒评Darwin在SuperCLUE榜单表现:数学科学推理第二,开源模型中居首

    <h2> Resumen </h2> <p>El 6 de noviembre de 2026, cuatro medios coreanos (Chosun Biz, Economist Korea, Digital Daily y AI Times) informaron que <a href="https://huggingface.co/FINAL-Bench/Darwin-180B-RSI-R3" rel="noopener noreferrer">Darwin-180B-RSI-R3</a>, el modelo de razonamien…

  4. dev.to — LLM tag TIER_1 English(EN) · AI OpenFree ·

    Darwin-180B-RSI 在 SuperCLUE(2026年11月)数学和科学推理方面排名第一的开放权重模型

    <h2> TL;DR </h2> <p>SuperCLUE, China's most widely cited LLM evaluation, published its November 2026 general leaderboard on November 5. Nineteen models were scored, including Gemini-4-Argon, GPT-6.1-Sol, Grok-4.7, Kimi-K3.1-Pro, DeepSeek-V4.1-Flash, GLM-5.3 and Qwen3.8-Max. <a hr…

  5. dev.to — LLM tag TIER_1 한국어(KO) · Vidraft_lab ·

    Darwin-180B-RSI 在中国 SuperCLUE 11月评估中 数学/科学推理开源模型排名第一:自我提升超越父模型

    <h2> TL;DR </h2> <p>중국 SuperCLUE가 11월 5일 2026년 11월 종합 리더보드를 공개했습니다. Gemini-4-Argon, GPT-6.1-Sol, Grok-4.7, Kimi-K3.1-Pro, DeepSeek-V4.1-Flash, GLM-5.3, Qwen3.8-Max 등 19개 모델이 올랐습니다. 비드래프트의 오픈 가중치 모델 <a href="https://huggingface.co/FINAL-Bench/Darwin-180B-RSI-R3" rel="noopener nore…