PulseAugur
中
实时 08:30:58
English(EN) ⚖️ Open vs proprietary, today Open-weight: Step 5 Preview - 28.5 Proprietary: Gemini 4 Carbon - 58.3 Gap: 29.8 points · and 4x cheaper per 1M output tokens http

开放权重模型在基准测试中落后于 Gemini 4 Carbon,但成本更低

一个开放权重模型在一个基准测试中取得了 28.5 分,而专有模型 Gemini 4 Carbon 的得分是 58.3 分。该开放权重模型每百万输出 token 的成本效益也是其四倍。这次比较突显了开放权重模型和专有大型语言模型之间显著的性能差距。 AI

影响 突显了开放权重模型和专有大型语言模型之间的成本效益权衡,暗示了更经济实惠的 AI 解决方案的潜力。

排序理由 开放权重模型与专有模型在基准测试分数上的比较。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 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 Gemini 4 Carbon,但成本更低

本文如何被排名

Signal score
18 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
开放权重模型与专有模型在基准测试分数上的比较。[lever_c_demoted from research: 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
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]

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

    ⚖️ 开放模型 vs 闭源模型,今日开放权重:Step 5 预览 - 28.5 闭源模型:Gemini 4 Carbon - 58.3 差距:29.8 分 · 且每 100 万输出 token 便宜 4 倍 http

    ⚖️ Open vs proprietary, today Open-weight: Step 5 Preview - 28.5 Proprietary: Gemini 4 Carbon - 58.3 Gap: 29.8 points · and 4x cheaper per 1M output tokens https:// olud.ai/leaderboard.html # OpenSource # AI # LLM