PulseAugur
中
实时 18:41:39
English(EN) 📊 DeepSeek V4 Flash 0420 (Max) — the actual numbers GPQA: 89.4% Humanity's Last Exam: 34.8% Long Context Reasoning: 74.3% SciCode: 45.3% 💰 144 intelligence poin

DeepSeek V4 Flash 0420 取得强劲基准分数

作者 PulseAugur 编辑部 · [1 个来源] ·

DeepSeek V4 Flash 0420 (Max) 在多项基准测试中取得了显著分数，包括 GPQA 的 89.4% 和 SciCode 的 45.3%。该模型在长上下文推理方面也表现出色，得分为 74.3%。这些结果使 DeepSeek V4 Flash 0420 成为开源 AI 领域中的有力竞争者，每美元拥有 144 智能点。 AI

影响 为开源模型设定了新的性能基准，可能影响未来的开发和采用。

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_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 V4 Flash 0420 取得强劲基准分数

本文如何被排名

Signal score
1 / 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_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
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

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 Flash 0420 (Max) — 实际分数 GPQA: 89.4% 人类最后考试: 34.8% 长上下文推理: 74.3% SciCode: 45.3% 💰 144 智能点

    📊 DeepSeek V4 Flash 0420 (Max) — the actual numbers GPQA: 89.4% Humanity's Last Exam: 34.8% Long Context Reasoning: 74.3% SciCode: 45.3% 💰 144 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSou…

    链接 olud.ai/leaderboard.html

相关实体

相关话题