PulseAugur
EN
LIVE 06:00:32

DeepSeek V4 Pro 0813 achieves strong benchmark scores

By PulseAugur Editorial · [1 sources] ·

DeepSeek V4 Pro 0813 has achieved notable scores on several benchmarks, including 92.8% on GPQA and 80.3% on Long Context Reasoning. The model also reached 51% on SciCode and 41% on Humanity's Last Exam. These results were independently measured, indicating a performance of 81.1 tokens per second and 18.3 intelligence points per dollar. AI

IMPACT Sets new benchmark scores for reasoning and long context, potentially influencing future model development.

RANK_REASON The item reports benchmark scores for an AI model, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

DeepSeek V4 Pro 0813 achieves strong benchmark scores

How we ranked this

Signal score
9 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item reports benchmark scores for an AI model, which falls under research. [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.

Full methodology in our editorial standards.

COVERAGE [1]

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

    📊 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 (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…

    LINKS olud.ai/leaderboard.html

RELATED ENTITIES

RELATED TOPICS