PulseAugur
中
实时 19:09:48
English(EN) ⚖️ Open vs proprietary, today Open-weight: Qwen3.8 Max (0902) - 45.4 Proprietary: Claude Sonnet 5.5 - 56 Gap: 10.6 points · and 2x cheaper per 1M output tokens

开放权重模型在基准测试中落后于专有模型,但提供成本节省

对开放权重模型和专有大型语言模型的比较显示,开放权重模型 Kimi K3 得分为 43.6,而专有模型 Claude Sonnet 5.5 得分为 56,差距为 12.4 分。另一项比较显示,开放权重模型 Qwen3.8 Max (0902) 得分为 45.4,而 Claude Sonnet 5.5 得分为 56,差距为 10.6 分。与 Claude Sonnet 5.5 相比,Qwen 模型每百万输出令牌的成本也低一倍。 AI

影响 突出了开放权重和专有大型语言模型之间的性能和成本权衡,为用户选择提供信息。

排序理由 该集群由社交媒体帖子组成,比较了不同大型语言模型的基准分数,而不是实验室的直接发布或官方公告。

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

开放权重模型在基准测试中落后于专有模型,但提供成本节省

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
Commentary
该集群由社交媒体帖子组成,比较了不同大型语言模型的基准分数,而不是实验室的直接发布或官方公告。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, other
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
7 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 [3]

  1. Mastodon — sigmoid.social TIER_1 English(EN) · [email protected] ·

    ⚖️ 开放模型 vs 专有模型,今日开放权重:GLM 5.3 Flash - 41.8 专有模型:Claude Sonnet 5.5 - 56 差距:14.2 分 · 且每百万输出 token 便宜 20 倍 http

    ⚖️ Open vs proprietary, today Open-weight: GLM 5.3 Flash - 41.8 Proprietary: Claude Sonnet 5.5 - 56 Gap: 14.2 points · and 20x cheaper per 1M output tokens https:// olud.ai/leaderboard.html # OpenSource # AI # LLM

  2. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    ⚖️ 开放模型 vs 专有模型,今日开放权重:Kimi K3 - 43.6 专有模型:Claude Sonnet 5.5 - 56 差距:12.4 分 https:// olud.ai/leaderboard.html # OpenSource #

    ⚖️ Open vs proprietary, today Open-weight: Kimi K3 - 43.6 Proprietary: Claude Sonnet 5.5 - 56 Gap: 12.4 points https:// olud.ai/leaderboard.html # OpenSource # AI # LLM

  3. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    ⚖️ 开放模型 vs 专有模型,今日开放权重:Qwen3.8 Max (0902) - 45.4 专有模型:Claude Sonnet 5.5 - 56 差距:10.6分 · 且每100万输出token便宜2倍

    ⚖️ Open vs proprietary, today Open-weight: Qwen3.8 Max (0902) - 45.4 Proprietary: Claude Sonnet 5.5 - 56 Gap: 10.6 points · and 2x cheaper per 1M output tokens https:// olud.ai/leaderboard.html # OpenSource # AI # LLM