PulseAugur
实时 06:01:10
English(EN) 📊 DeepSeek V4 Pro 0813 (Reasoning, Max Effort) — the actual numbers GPQA: 92.8% Humanity's Last Exam: 41% Long Context Reasoning: 80.3% SciCode: 51% ⚡ 81.1 toke

DeepSeek V4 Pro 0813 在基准测试中取得强劲分数

DeepSeek V4 Pro 0813 在多项基准测试中取得了显著分数,包括 GPQA 的 92.8% 和长上下文推理的 80.3%。该模型在 SciCode 上达到 51%,在人类最后考试上达到 41%。这些结果是独立测量的,表明每秒性能为 81.1 个 token,每美元智能点数为 18.3。 AI

影响 在推理和长上下文方面设定了新的基准分数,可能影响未来的模型开发。

排序理由 该项目报告了 AI 模型的基准分数,属于研究范畴。[lever_c_从研究降级: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 V4 Pro 0813 在基准测试中取得强劲分数

本文如何被排名

Signal score
9 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目报告了 AI 模型的基准分数,属于研究范畴。[lever_c_从研究降级: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 V4 Pro 0813 (推理,尽最大努力) — 实际数字 GPQA: 92.8% 人类最后考试: 41% 长上下文推理: 80.3% SciCode: 51% ⚡ 81.1 toke

    📊 DeepSeek V4 Pro 0813 (Reasoning, Max Effort) — the actual numbers GPQA: 92.8% Humanity's Last Exam: 41% Long Context Reasoning: 80.3% SciCode: 51% ⚡ 81.1 tokens/sec 💰 18.3 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.ht…