PulseAugur
中
实时 13:52:49
English(EN) DeepSeek R1 0528 (May '25) scores 81.3% on GPQA, but its 6.3 intelligence points per dollar shows how much reasoning you get for the cost. See the full independ

DeepSeek R1 0528 在 GPQA 基准测试中达到 81.3%

作者 PulseAugur 编辑部 · [1 个来源] ·

DeepSeek R1 0528，一个于 2025 年 5 月发布的模型，在 GPQA 基准测试中取得了 81.3% 的分数。该模型的性能还表明其每花费一美元的成本效益为 6.3 个智能点数。有关此独立基准测试的更多详细信息可在 olud.ai 上找到。 AI

影响 提供了关于人工智能推理能力成本效益的数据点。

排序理由 该集群报告了一个 AI 模型的特定基准测试分数，属于研究范畴。[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 →

DeepSeek R1 0528 在 GPQA 基准测试中达到 81.3%

本文如何被排名

Signal score
16 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群报告了一个 AI 模型的特定基准测试分数，属于研究范畴。[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, paper
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 ·

    DeepSeek R1 0528 (May '25) scores 81.3% on GPQA, but its 6.3 intelligence points per dollar shows how much reasoning you get for the cost. See the full independ

    DeepSeek R1 0528 (May '25) scores 81.3% on GPQA, but its 6.3 intelligence points per dollar shows how much reasoning you get for the cost. See the full independent benchmark breakdown on https:// olud.ai . https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI

    链接 olud.ai olud.ai/leaderboard.html

相关实体

相关话题